/
clulab_publications.bib
2336 lines (2303 loc) · 129 KB
/
clulab_publications.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@article{Vacareanu2024GeneralVerificationLLM,
title={General Purpose Verification for Chain of Thought Prompting},
author={Robert Vacareanu and Anurag Pratik and Evangelia Spiliopoulou and Zheng Qi and Giovanni Paolini and Neha Anna John and Jie Ma and Yassine Benajiba and Miguel Ballesteros},
journal={ArXiv},
year={2024},
volume={abs/2405.00204},
url={https://arxiv.org/pdf/2405.00204.pdf}
}
@article{Vacareanu2024LLMsRegression,
title={From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples},
author={Robert Vacareanu and Vlad-Andrei Negru and Vasile Suciu and Mihai Surdeanu},
journal={ArXiv},
year={2024},
volume={abs/2404.07544},
url={https://arxiv.org/pdf/2404.07544.pdf}
}
@inproceedings{vacareanu2024softrules,
title = "Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification",
author = "Robert Vacareanu and Fahmida Alam and Md Asiful Islam and Haris Riaz and Mihai Surdeanu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/pdf/2403.03305.pdf",
abstract = "This paper introduces a novel neuro-symbolic architecture for relation classification (RC) that combines rule-based methods with contemporary deep learning techniques. This approach capitalizes on the strengths of both paradigms: the adaptability of rule-based systems and the generalization power of neural networks. Our architecture consists of two components: a declarative rule-based model for transparent classification and a neural component to enhance rule generalizability through semantic text matching. Notably, our semantic matcher is trained in an unsupervised domain-agnostic way, solely with synthetic data. Further, these components are loosely coupled, allowing for rule modifications without retraining the semantic matcher. In our evaluation, we focused on two few-shot relation classification datasets: Few-Shot TACRED and a Few-Shot version of NYT29. We show that our proposed method outperforms previous state-of-the-art models in three out of four settings, despite not seeing any human-annotated training data. Further, we show that our approach remains modular and pliable, i.e., the corresponding rules can be locally modified to improve the overall model. Human interventions to the rules for the TACRED relation \texttt{org:parents} boost the performance on that relation by as much as 26\% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component.",
}
@inproceedings{vacareanu2024ActiveLearningNER,
title = "Active Learning Design Choices for NER with Transformers",
author = "Robert Vacareanu and Enrique Noriega-Atala and Gus Hahn-Powell and Marco A. Valenzuela-Escarcega and Mihai Surdeanu ",
booktitle = "Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation",
month = may,
year = "2024",
address = "Torino, Italy",
publisher = "European Language Resources Association",
abstract = "We explore multiple important choices that have not been analyzed in conjunction regarding active learning for token classification using transformer networks. These choices are: (i) how to select what to annotate, (ii) decide whether to annotate entire sentences or smaller sentence fragments, (iii) how to train with incomplete annotations at token-level, and (iv) how to select the initial seed dataset. We explore whether annotating at sub-sentence level can translate to an improved downstream performance by considering two different sub-sentence annotation strategies: (i) entity-level, and (ii) token-level. These approaches result in some sentences being only partially annotated. To address this issue, we introduce and evaluate multiple strategies to deal with partially-annotated sentences during the training process. We show that annotating at the sub-sentence level achieves comparable or better performance than sentence-level annotations with a smaller number of annotated tokens. We then explore the extent to which the performance gap remains once accounting for the annotation time and found that both annotation schemes perform similarly.",
}
@inproceedings{vacareanu-etal-2024-weak,
title = "A Weak Supervision Approach for Few-Shot Aspect Based Sentiment Analysis",
author = "Vacareanu, Robert and
Varia, Siddharth and
Halder, Kishaloy and
Wang, Shuai and
Paolini, Giovanni and
Anna John, Neha and
Ballesteros, Miguel and
Muresan, Smaranda",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.167",
pages = "2734--2752",
abstract = "We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks. We propose a pipeline approach to construct a noisy ABSA dataset, and we use it to adapt a pre-trained sequence-to-sequence model to the ABSA tasks. We test the resulting model on three widely used ABSA datasets, before and after fine-tuning. Our proposed method preserves the full fine-tuning performance while showing significant improvements (15.84 absolute F1) in the few-shot learning scenario for the harder tasks. In zero-shot (i.e., without fine-tuning), our method outperforms the previous state of the art on the aspect extraction sentiment classification (AESC) task and is, additionally, capable of performing the harder aspect sentiment triplet extraction (ASTE) task.",
}
@inproceedings{wang2024naaclfindings,
title = "Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains",
author = "Wang, Zijie and Rashid, Farzana and Blanco, Eduardo",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics"
}
@inproceedings{golchin2024time,
title={Time Travel in {LLM}s: Tracing Data Contamination in Large Language Models},
author={Shahriar Golchin and Mihai Surdeanu},
booktitle={Proceedings of the Twelfth International Conference on Learning Representations (ICLR)},
year={2024},
url={https://openreview.net/forum?id=2Rwq6c3tvr}
}
@inproceedings{fahmida2024fs-meta-dataset,
title = "Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation",
author = "Fahmida Alam and Md Asiful Islam and Robert Vacareanu and Mihai Surdeanu ",
booktitle = "Proceedings of the Fourteenth Language Resources and Evaluation Conference",
month = may,
year = "2024",
address = "Torino, Italy",
publisher = "European Language Resources Association",
url = "http://arxiv.org/abs/2404.04445",
abstract = "We introduce a meta dataset for few-shot relation extraction, which includes two datasets derived from existing supervised relation extraction datasets – NYT29 (Takanobu et al. , 2019 ; Nayak and Ng , 2020) and WIKIDATA (Sorokin and Gurevych, 2017) – as well as a few-shot form of the TACRED dataset (Sabo et al., 2021). Importantly, all these few-shot datasets were generated under realistic assumptions such as: the test relations are different from any relations a model might have seen before, limited training data, and a preponderance of candidate relation mentions that do not correspond to any of the relations of interest. Using this large resource, we conduct a comprehensive evaluation of six recent few-shot relation extraction methods, and observe that no method comes out as a clear winner. Further, the overall performance on this task is low, indicating substantial need for future research. We release all versions of the data, i.e., both supervised and few-shot, for future research."
}
@inproceedings{riaz2024ellen,
title = "ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition",
author = "Haris Riaz and Razvan-Gabriel Dumitru and Mihai Surdeanu",
booktitle = "Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation",
month = may,
year = "2024",
address = "Torino, Italy",
publisher = "European Language Resources Association",
url = "https://arxiv.org/pdf/2403.17385.pdf",
abstract = "In this work, we revisit the problem of semi-supervised named entity recognition (NER) focusing on extremely light supervision, consisting of a lexicon containing only 10 examples per class. We introduce ELLEN, a simple, fully modular, neuro-symbolic method that blends fine-tuned language models with linguistic rules. These rules include insights such as ''One Sense Per Discourse'', using a Masked Language Model as an unsupervised NER, leveraging part-of-speech tags to identify and eliminate unlabeled entities as false negatives, and other intuitions about classifier confidence scores in local and global context. ELLEN achieves very strong performance on the CoNLL-2003 dataset when using the minimal supervision from the lexicon above. It also outperforms most existing (and considerably more complex) semi-supervised NER methods under the same supervision settings commonly used in the literature (i.e., 5% of the training data). Further, we evaluate our CoNLL-2003 model in a zero-shot scenario on WNUT-17 where we find that it outperforms GPT-3.5 and achieves comparable performance to GPT-4. In a zero-shot setting, ELLEN also achieves over 75% of the performance of a strong, fully supervised model trained on gold data. Our code is available at: https://github.com/hriaz17/ELLEN",
}
@inproceedings{anaissy-icaart2024,
title = "On Learning Bipolar Gradual Argumentation Semantics with Neural Networks",
author = "Caren Al Anaissy and Sandeep Suntwal and Mihai Surdeanu and Srdjan Vesic",
booktitle = "Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART)",
year = "2024",
url = "https://clulab.org/papers/icaart2024.pdf",
abstract = "Computational argumentation has evolved as a key area in artificial intelligence, used to analyze aspects of thinking, making decisions, and conversing. As a result, it is currently employed in a variety of real-world contexts, from legal reasoning to intelligence analysis. An argumentation framework is modelled as a graph where the nodes represent arguments and the edges of the graph represent relations (i.e., supports, attacks) between nodes. In this work, we investigate the ability of neural network methods to learn a gradual bipolar argumentation semantics, which allows for both supports and attacks. We begin by calculating the acceptability degrees for graph nodes. These scores are generated using Quantitative Argumentation Debate (QuAD) argumentation semantics. We apply this approach to two benchmark datasets: Twelve Angry Men and Debate- pedia. Using this data, we train and evaluate the performance of three benchmark architectures: Multilayer Perceptron (MLP), Graph Convolution Network (GCN), and Graph Attention Network (GAT) to learn the acceptability degree scores produced by the QuAD semantics. Our results show that these neural network methods can learn bipolar gradual argumentation semantics. The models trained on GCN architecture perform better than the other two architectures underscoring the importance of modelling argumentation graphs explicitly."
}
@inproceedings{
pyarelal2023the,
title={The To{MCAT} Dataset},
author={Adarsh Pyarelal and Eric Duong and Caleb Jones Shibu and Paulo Soares and Savannah Boyd and Payal Khosla and Valeria Pfeifer and Diheng Zhang and Eric S Andrews and Rick Champlin and Vincent Paul Raymond and Meghavarshini Krishnaswamy and Clayton Morrison and Emily Butler and Kobus Barnard},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2023},
url={https://openreview.net/forum?id=ZJWQfgXQb6}
}
@inproceedings{qamar-etal-2023-speaking,
title = "Who is Speaking? Speaker-Aware Multiparty Dialogue Act Classification",
author = "Qamar, Ayesha and
Pyarelal, Adarsh and
Huang, Ruihong",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.678",
pages = "10122--10135",
abstract = "Utterances do not occur in isolation in dialogues; it is essential to have the information of who the speaker of an utterance is to be able to recover the speaker{'}s intention with respect to the surrounding context. Beyond simply capturing speaker switches, identifying how speakers interact with each other in a dialogue is crucial to understanding conversational flow. This becomes increasingly important and simultaneously difficult to model when more than two interlocutors take part in a conversation. To overcome this challenge, we propose to explicitly add speaker awareness to each utterance representation. To that end, we use a graph neural network to model how each speaker is behaving within the local context of a conversation. The speaker representations learned this way are then used to update their respective utterance representations. We experiment with both multiparticipant and dyadic conversations on the MRDA and SwDA datasets and show the effectiveness of our approach.",
}
@inproceedings{miah-etal-2023-hierarchical,
title = "Hierarchical Fusion for Online Multimodal Dialog Act Classification",
author = "Miah, Md Messal Monem and
Pyarelal, Adarsh and
Huang, Ruihong",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.505",
pages = "7532--7545",
abstract = "We propose a framework for online multimodal dialog act (DA) classification based on raw audio and ASR-generated transcriptions of current and past utterances. Existing multimodal DA classification approaches are limited by ineffective audio modeling and late-stage fusion. We showcase significant improvements in multimodal DA classification by integrating modalities at a more granular level and incorporating recent advancements in large language and audio models for audio feature extraction. We further investigate the effectiveness of self-attention and cross-attention mechanisms in modeling utterances and dialogs for DA classification. We achieve a substantial increase of 3 percentage points in the F1 score relative to current state-of-the-art models on two prominent DA classification datasets, MRDA and EMOTyDA.",
}
@inproceedings{cooper-etal-2023-hiding,
title = "Hiding in Plain Sight: Tweets with Hate Speech Masked by Homoglyphs",
author = "Cooper, Portia and
Surdeanu, Mihai and
Blanco, Eduardo",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.192",
doi = "10.18653/v1/2023.findings-emnlp.192",
pages = "2922--2929",
abstract = "To avoid detection by current NLP monitoring applications, progenitors of hate speech often replace one or more letters in offensive words with homoglyphs, visually similar Unicode characters. Harvesting real-world hate speech containing homoglyphs is challenging due to the vast replacement possibilities. We developed a character substitution scraping method and assembled the Offensive Tweets with Homoglyphs (OTH) Dataset (N=90,788) with more than 1.5 million occurrences of 1,281 non-Latin characters (emojis excluded). In an annotated sample (n=700), 40.14{\%} of the tweets were found to contain hate speech. We assessed the performance of seven transformer-based hate speech detection models and found that they performed poorly in a zero-shot setting (F1 scores between 0.04 and 0.52) but normalizing the data dramatically improved detection (F1 scores between 0.59 and 0.71). Training the models using the annotated data further boosted performance (highest micro-averaged F1 score=0.88, using five-fold cross validation). This study indicates that a dataset containing homoglyphs known and unknown to the scraping script can be collected, and that neural models can be trained to recognize camouflaged real-world hate speech.",
}
@inproceedings{kwak-et-al-nllp2023-error-analysis,
title = "Transferring Legal Natural Language Inference Model from a US State to Another: What Makes It So Hard?",
author = "Alice Kwak and Gaetano Forte and Derek Bambauer and Mihai Surdeanu",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2023",
month = dec,
year = "2023",
url = "https://clulab.org/papers/nllp2023_kwak-et-al.pdf",
abstract = "This study investigates whether a legal natural language inference (NLI) model trained on the data from one US state can be transferred to another state. We fine-tuned a pre-trained model on the task of evaluating the validity of legal will statements, once with the dataset containing the Tennessee wills and once with the dataset containing the Idaho wills. Each model’s performance on the in-domain setting and the out-of-domain setting are compared to see if the models can across the states. We found that the model trained on one US state can be mostly transferred to another state. However, it is clear that the model’s performance drops in the out-of-domain setting. The F1 scores of the Tennessee model and the Idaho model are 96.41 and 92.03 when predicting the data from the same state, but they drop to 66.32 and 81.60 when predicting the data from another state. Subsequent error analysis revealed that there are two major sources of errors. First, the model fails to recognize equivalent laws across states when there are stylistic differences between laws. Second, difference in statutory section numbering system between the states makes it difficult for the model to locate laws relevant to the cases being predicted on. This analysis provides insights on how the future NLI system can be improved. Also, our findings offer empirical support to legal experts advocating the standardization of legal documents.",
}
@inproceedings{kwak-et-al-emnlp2023-ie4wills,
title = "Information Extraction from Legal Wills: How Well Does GPT-4 Do?",
author = "Alice Kwak and Cheonkam Jeong and Gaetano Forte and Derek Bambauer and Clayton Morrison and Mihai Surdeanu",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
url = "https://clulab.org/papers/emnlp2023_kwak-et-al.pdf",
abstract = "This work presents a manually annotated dataset for Information Extraction (IE) from legal wills, and relevant in-context learning experiments on the dataset. The dataset consists of entities, binary relations between the entities (e.g., relations between testator and beneficiary), and n-ary events (e.g., bequest) extracted from 45 legal wills from two US states. This dataset can serve as a foundation for downstream tasks in the legal domain. Another use case of this dataset is evaluating the performance of large language models (LLMs) on this IE task. We evaluated GPT-4 with our dataset to investigate its ability to extract information from legal wills. Our evaluation result demonstrates that the model is capable of handling the task reasonably well. When given instructions and examples as a prompt, GPT-4 shows decent performance for both entity extraction and relation extraction tasks. Nevertheless, the evaluation result also reveals that the model is not perfect. We observed inconsistent outputs (given a prompt) as well as prompt over-generalization.",
}
@inproceedings{rahimi-surdeanu-2023-improving,
title = "Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates",
author = "Rahimi, Mahdi and
Surdeanu, Mihai",
booktitle = "Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.repl4nlp-1.16",
pages = "187--195",
abstract = "While fully supervised relation classification (RC) models perform well on large-scale datasets, their performance drops drastically in low-resource settings. As generating annotated examples are expensive, recent zero-shot methods have been proposed that reformulate RC into other NLP tasks for which supervision exists such as textual entailment. However, these methods rely on templates that are manually created which is costly and requires domain expertise. In this paper, we present a novel strategy for template generation for relation classification, which is based on adapting Harris{'} distributional similarity principle to templates encoded using contextualized representations. Further, we perform empirical evaluation of different strategies for combining the automatically acquired templates with manual templates. The experimental results on TACRED show that our approach not only performs better than the zero-shot RC methods that only use manual templates, but also that it achieves state-of-the-art performance for zero-shot TACRED at 64.3 F1 score.",
}
@inproceedings{george-surdeanu-2023-sexually,
title = "It{'}s not Sexually Suggestive; It{'}s Educative | Separating Sex Education from Suggestive Content on {T}ik{T}ok Videos",
author = "George, Enfa and
Surdeanu, Mihai",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.365",
pages = "5904--5915",
abstract = "We introduce SexTok, a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator{'}s point of view), sex-educational content, or neither. Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok. Children{'}s exposure to sexually suggestive videos has been shown to have adversarial effects on their development (Collins et al. 2017). Meanwhile, virtual sex education, especially on subjects that are more relevant to the LGBTQIA+ community, is very valuable (Mitchell et al. 2014). The platform{'}s current system removes/punishes some of both types of videos, even though they serve different purposes. Our dataset contains video URLs, and it is also audio transcribed. To validate its importance, we explore two transformer-based models for classifying the videos. Our preliminary results suggest that the task of distinguishing between these types of videos is learnable but challenging. These experiments suggest that this dataset is meaningful and invites further study on the subject.",
}
@inproceedings{Vacareanu2022PatternRankJR,
title = {PatternRank: Jointly Ranking Patterns and Extractions for Relation Extraction Using Graph-Based Algorithms},
author = {Robert Vacareanu and Dane Bell and Mihai Surdeanu},
booktitle = {PANDL},
abstract="{In this paper we revisit the direction of using lexico-syntactic patterns for relation extraction instead of today's ubiquitous neural classifiers. We propose a semi-supervised graph-based algorithm for pattern acquisition that scores patterns and the relations they extract jointly, using a variant of PageRank. We insert light supervision in the form of seed patterns or relations, and model it with several custom teleportation probabilities that bias random-walk scores of patterns/relations based on their proximity to correct information. We evaluate our approach on Few-Shot TACRED, and show that our method outperforms (or performs competitively with) more expensive and opaque deep neural networks. Lastly, we thoroughly compare our proposed approach with the seminal RlogF pattern acquisition algorithm of, showing that it outperforms it for all the hyper parameters tested, in all settings. }",
url = {https://aclanthology.org/2022.pandl-1.1.pdf},
year = {2022}
}
@article{Vacareanu2022AHI,
title = {A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction},
author = {Robert Vacareanu and George Caique Gouveia Barbosa and Enrique Noriega-Atala and Gus Hahn-Powell and Rebecca Sharp and Marco Antonio Valenzuela-Escarcega and Mihai Surdeanu},
journal = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations},
abstract = "{We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis.Users of our system can specify their requirements through the use of examples,which are collected with a search interface.The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system.Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns.Our code, demo, and documentation is available at https://clulab.github.io/odinsynth.}",
url = {https://aclanthology.org/2022.naacl-demo.8.pdf},
year = {2022}
}
@inproceedings{nitschke-etal-2022-rule,
title = "Rule Based Event Extraction for Artificial Social Intelligence",
author = "Nitschke, Remo and
Wang, Yuwei and
Chen, Chen and
Pyarelal, Adarsh and
Sharp, Rebecca",
booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.pandl-1.9",
pages = "71--84",
abstract = "Natural language (as opposed to structured communication modes
such as Morse code) is by far the most common mode of communication
between humans, and can thus provide significant insight into both
individual mental states and interpersonal dynamics. As part of
DARPA{'}s Artificial Social Intelligence for Successful Teams (ASIST)
program, we are developing an AI agent team member that constructs and
maintains models of their human teammates and provides appropriate
task-relevant advice to improve team processes and mission performance.
One of the key components of this agent is a module that uses a
rule-based approach to extract task-relevant events from natural
language utterances in real time, and publish them for consumption by
downstream components. In this case study, we evaluate the performance
of our rule-based event extraction system on a recently conducted ASIST
experiment consisting of a simulated urban search and rescue mission in
Minecraft. We compare the performance of our approach with that of a
zero-shot neural classifier, and find that our approach outperforms the
classifier for all event types, even when the classifier is used in an
oracle setting where it knows how many events should be extracted from
each utterance.",
}
@inproceedings{zupon2020capsnet,
title={An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios},
author={Zupon, Andrew and Rafique, Faiz and Surdeanu, Mihai},
booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP},
url={http://clulab.org/papers/insights2020-capsnet.pdf},
year={2020}
}
@inproceedings{liang2020can,
title={Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?},
author={Liang, Zhengzhong and Surdeanu, Mihai},
booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop on Insights from Negative Results in NLP},
url={http://clulab.org/papers/emnlp2020-can.pdf},
year={2020}
}
@article{van2020covid,
title={The Language of Food during the Pandemic: Hints about the Dietary Effects of Covid-19},
author={Hoang Van and Ahmad Musa and Mihai Surdeanu and Stephen Kobourov},
journal={arXiv preprint arXiv:2010.07466},
url={https://arxiv.org/abs/2010.07466},
year={2020}
}
@article{liang2020using,
title={Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering},
author={Liang, Zhengzhong and Zhao, Yiyun and Surdeanu, Mihai},
journal={arXiv preprint arXiv:2009.10791},
url = "https://arxiv.org/abs/2009.10791",
year={2020}
}
@InProceedings{jansen-EtAl:2016:COLING,
author = {Jansen, Peter and Balasubramanian, Niranjan and Surdeanu, Mihai and Clark, Peter},
title = {What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams},
booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
month = {December},
year = {2016},
address = {Osaka, Japan},
publisher = {The COLING 2016 Organizing Committee},
pages = {2956-2965},
url = {http://aclweb.org/anthology/C16-1278},
url_Data = {http://allenai.org/data.html},
}
@inproceedings{valenzuela2015identifying,
title={Identifying meaningful citations},
author={Valenzuela, Marco and Ha, Vu and Etzioni, Oren},
booktitle={Proceedings of the "Scholarly Big Data: AI Perspectives, Challenges, and Ideas" Workshop at the Twenty-Ninth AAAI Conference on Artificial Intelligence},
year={2015},
url={http://ai2-website.s3.amazonaws.com/publications/ValenzuelaHaMeaningfulCitations.pdf}
}
@inproceedings{Jansen:14,
year = {2014},
author = {Jansen, Peter and Surdeanu, Mihai and Clark, Peter},
booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)},
title = {Discourse Complements Lexical Semantics for Non-factoid Answer Reranking},
url = {http://clulab.org/papers/acl2014.pdf},
url_Code_And_Data = {http://nlp.sista.arizona.edu/releases/acl2014/},
url_Slides = {http://nlp.sista.arizona.edu/releases/acl2014/},
}
@inproceedings{Manning:14,
year = {2014},
author = {Manning, Christopher D. and Surdeanu, Mihai and Bauer, John and Finkel, Jenny and Bethard, Steven J. and McClosky, David},
booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)},
title = {The Stanford CoreNLP Natural Language Processing Toolkit},
url = {http://clulab.org/papers/acl2014-corenlp.pdf},
url_Code = {http://nlp.stanford.edu/software/corenlp.shtml},
}
@InProceedings{Valenzuela:15,
author = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell and Thomas Hicks and Mihai Surdeanu},
title = {A Domain-independent Rule-based Framework for Event Extraction},
booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Assian Federation of Natural Language Processing: Software Demonstrations (ACL-IJCNLP)},
year = {2015},
url = {http://clulab.org/papers/acl2015.pdf},
url_Code = {https://github.com/sistanlp/processors},
}
@inproceedings{Fried:14,
year = {2014},
author = {Fried, Daniel and Surdeanu, Mihai and Kobourov, Stephen and Hingle, Melanie and Bell, Dane},
booktitle = {Proceedings of the 2014 IEEE International Conference on Big Data},
title = {Analyzing the Language of Food on Social Media},
url = {http://clulab.org/papers/bigdata2014.pdf},
url_Supplmental_Material = {http://arxiv.org/abs/1409.2195},
url_Demo = {https://sites.google.com/site/twitter4food/},
}
@InProceedings{Valenzuela:16b,
author = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell and Dane Bell and Mihai Surdeanu},
title = {SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction},
booktitle = {Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016)},
year = {2016},
url = {https://arxiv.org/abs/1606.09604},
}
@InProceedings{HahnPowell:16,
author = {Gustave Hahn-Powell and Dane Bell and Valenzuela-Escarcega, Marco A. and Mihai Surdeanu},
title = {This before That: Causal Precedence in the Biomedical Domain},
booktitle = {Proceedings of the 2016 Workshop on Biomedical Natural Language Processing (BioNLP 2016)},
year = {2016},
url = {https://arxiv.org/abs/1606.08089},
note = {Latest results can be found at {https://repository.arizona.edu/handle/10150/630562}}
}
@Article{Zapirain:13,
author = {Benat Zapirain and Eneko Agirre and Lluis Marquez and Mihai Surdeanu},
title = {Selectional Preferences for Semantic Role Classification},
journal = {Computational Linguistics},
volume = {39},
number = {3},
year = {2013},
url = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00145},
}
@Article{Lee:13,
author = {Heeyoung Lee and Angel Chang and Yves Peirsman and Nathanael Chambers and Mihai Surdeanu and Dan Jurafsky},
title = {Deterministic coreference resolution based on entity-centric, precision-ranked rules},
journal = {Computational Linguistics},
volume = {39},
number = {4},
year = {2013},
url = {http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00152},
}
@inproceedings{Sharp2016,
year = {2016},
author = {Sharp, Rebecca and Mihai Surdeanu and Peter Jansen and Peter Clark and Michael Hammond},
booktitle = {Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
title = {Creating Causal Embeddings for Question Answering with Minimal Supervision},
url = {http://arxiv.org/abs/1609.08097},
url_Data_and_Code = {http://clulab.org/data/emnlp2016-causal/},
}
@inproceedings{surdeanu2013-icail,
year = {2013},
author = {Mihai Surdeanu and Sara Jeruss},
booktitle = {Proceedings of the XIV International Conference on Artificial Intelligence and Law (ICAIL)},
title = {Identifying Patent Monetization Entities},
url = {http://clulab.org/papers/icail2013.pdf},
}
@inproceedings{Surdeanu:13,
year = {2013},
author = {Surdeanu, Mihai},
booktitle = {Proceedings of the TAC-KBP 2013 Workshop},
title = {Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling and Temporal Slot Filling},
url = {http://clulab.org/papers/kbp2013.pdf},
url_Slides_SF = {http://clulab.org/papers/kbp2013_sf.pdf},
url_Slides_TSF = {http://clulab.org/papers/kbp2013_tsf.pdf},
}
@inproceedings{SurdeanuHeng:14,
year = {2014},
author = {Surdeanu, Mihai and Heng, Ji},
booktitle = {Proceedings of the TAC-KBP 2014 Workshop},
title = {Overview of the English Slot Filling Track at the TAC2014 Knowledge Base Population Evaluation},
url = {http://clulab.org/papers/kbp2014_draft.pdf},
}
@inproceedings{Reschke:14,
year = {2014},
author = {Reschke, Kevin and Jankowiak, Martin and Surdeanu, Mihai and Manning, Christopher D. and Jurafsky, Dan},
booktitle = {Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC)},
title = {Event Extraction Using Distant Supervision},
url = {http://clulab.org/papers/lrec2014_ds.pdf},
url_Data = {http://nlp.stanford.edu/projects/dist-sup-event-extraction.shtml},
url_Slides = {http://clulab.org/papers/lrec2014_ds_slides.pdf}
}
@inproceedings{Lee:14,
year = {2014},
author = {Lee, Heeyoung and MacCartney, Bill and Surdeanu, Mihai and Jurafsky, Dan},
booktitle = {Proceedings of the 9th edition of the Language Resources and Evaluation Conference (LREC)},
title = {On the Importance of Text Analysis for Stock Price Prediction},
url = {http://clulab.org/papers/lrec2014_stocks.pdf},
url_Data = {http://nlp.stanford.edu/pubs/stock-event.html},
url_Slides = {http://clulab.org/papers/lrec2014_stocks_slides.pdf},
}
@InProceedings{Bell:16,
author = {Bell, Dane and Gustave Hahn-Powell and Marco A. Valenzuela-Escarcega and Gustave Hahn-Powell and Mihai Surdeanu},
title = {An Investigation of Coreference Phenomena in the Biomedical Domain},
booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},
year = {2016},
url = {http://clulab.org/papers/lrec2016-coref.pdf},
url_Code = {https://github.com/clulab/reach},
}
@InProceedings{Valenzuela:16,
author = {Valenzuela-Escarcega, Marco A. and Gustave Hahn-Powell and Mihai Surdeanu},
title = {Odin's Runes: A Rule Language for Information Extraction},
booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},
year = {2016},
url = {http://surdeanu.info/mihai/papers/lrec2016-odin.pdf},
url_Code = {https://github.com/sistanlp/processors},
}
@InProceedings{Bell:16b,
author = {Bell, Dane and Daniel Fried and Luwen Huangfu and Mihai Surdeanu and Stephen Kobourov},
title = {Towards Using Social Media to Identify Individuals at Risk for Preventable Chronic Illness},
booktitle = {Proceedings of the 10th edition of the Language Resources and Evaluation Conference (LREC)},
year = {2016},
url = {http://clulab.org/papers/lrec2016-t4f.pdf},
url_Code = {https://github.com/clulab/twitter4food},
}
@InProceedings{Surdeanu:15,
author = {Surdeanu, Mihai and Thomas Hicks and Marco A. Valenzuela-Escarcega},
title = {Two Practical Rhetorical Structure Theory Parsers},
booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations},
year = {2015},
url = {http://clulab.org/papers/naacl2015-discourse.pdf},
url_Code = {https://github.com/sistanlp/processors},
}
@InProceedings{Intxaurrondo:15,
author = {Intxaurrondo, Ander and Eneko Agirre and Oier Lopez de Lacalle and Mihai Surdeanu},
title = {Diamonds in the Rough: Event Extraction from Imperfect Microblog Data},
booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT)},
year = {2015},
url = {http://clulab.org/papers/naacl2015-ee.pdf},
url_Data = {http://ixa.eus/Ixa/Argitalpenak/Artikuluak/1425465524/publikoak/earthquake-kb-dataset.zip},
}
@InProceedings{Sharp:15,
author = {Sharp, Rebecca and Peter Jansen and Mihai Surdeanu and Peter Clark},
title = {Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering},
booktitle = {Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT)},
year = {2015},
url = {http://clulab.org/papers/naacl2015-qa.pdf},
url_Data_and_Some_Code = {http://surdeanu.cs.arizona.edu/mihai/papers/straw2gold.zip},
}
@inproceedings{intxaurrondo13,
year = {2013},
author = {Ander Intxaurrondo and Mihai Surdeanu and Oier Lopez de Lacalle and Eneko Agirre},
booktitle = {Proceedings of the 29th "Congreso de la Sociedad Espa{\~{n}}ola para el Procesamiento del Lenguaje Natural" (SEPLN 2013)},
title = {Removing Noisy Mentions for Distant Supervision},
url = {http://clulab.org/papers/sepln13.pdf},
}
@inproceedings{Tran:14,
year = {2014},
author = {Tran, Anh and Surdeanu, Mihai and Cohen, Paul},
booktitle = {Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM)},
title = {Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge},
url = {http://clulab.org/papers/starsem2014.pdf},
url_Slides = {http://clulab.org/papers/starsem2014_slides.pdf},
}
@article{Fried:2015,
author = {Daniel Fried and Peter Jansen and Gustave Hahn-Powell and Mihai
Surdeanu and Peter Clark},
title = {Higher-order Lexical Semantic Models for Non-factoid Answer
Reranking},
journal = {Transactions of the Association for Computational Linguistics},
volume = {3},
year = {2015},
keywords = {},
abstract = {Lexical semantic models provide robust performance for question
answering, but, in general, can only capitalize on direct evidence seen
during training. For example, monolingual alignment models acquire term
alignment probabilities from semi-structured data such as question-answer
pairs; neural network language models learn term embeddings from
unstructured text. All this knowledge is then used to estimate the semantic
similarity between question and answer candidates. We introduce a
higher-order formalism that allows all these lexical semantic models to
chain direct evidence to construct indirect associations between question
and answer texts, by casting the task as the traversal of graphs that encode
direct term associations. Using a corpus of 10,000 questions from Yahoo!
Answers, we experimentally demonstrate that higher-order methods are broadly
applicable to alignment and language models, across both word and syntactic
representations. We show that an important criterion for success is
controlling for the semantic drift that accumulates during graph traversal.
All in all, the proposed higher-order approach improves five out of the six
lexical semantic models investigated, with relative gains of up to +13\%
over their first-order variants. },
issn = {2307-387X},
url =
{https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/550},
pages = {197-210}
}
@inproceedings{Forbes:13,
year = {2013},
author = {Angus Forbes and Mihai Surdeanu and Peter Jansen and Jane Carrington},
booktitle = {Proceedings of the 3rd IEEE Workshop on Interactive Visual Text Analytics},
title = {Transmitting Narrative: An Interactive Shift-Summarization Tool for Improving Nurse Communication},
url = {http://clulab.org/papers/textvis2013.pdf},
}
@article{valenzuela2015description,
title={Description of the odin event extraction framework and rule language},
author={Valenzuela-Escarcega, Marco A and Hahn-Powell, Gus and Surdeanu, Mihai},
journal={arXiv preprint arXiv:1509.07513},
year={2015},
url={https://arxiv.org/pdf/1509.07513},
}
@InProceedings{Colin:NAACLHLT2013,
title={Bayesian modeling of scenes and captions},
author={Colin R. Dawson, Luca Del Pero, Clayton T. Morrison, Mihai Surdeanu, Gustave Hahn-Powell, Zachary Chapman and Kobus Barnard},
year={2013},
booktitle={Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2013), Workshop on Vision and Language (WVL)},
url_Slides={http://surdeanu.info/mihai/papers/wvl2013_slides.pdf},
}
@inproceedings{sharp2017tell,
title={Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification},
author={Sharp, Rebecca and Surdeanu, Mihai and Jansen, Peter and Valenzuela-Escarcega, Marco A and Clark, Peter and Hammond, Michael},
booktitle={Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
pages={69-79},
year={2017},
url={http://www.aclweb.org/anthology/K17-1009}
}
@article{jansen2017framing,
title={Framing QA as Building and Ranking Intersentence Answer Justifications},
author={Jansen, Peter and Sharp, Rebecca and Surdeanu, Mihai and Clark, Peter},
journal={Computational Linguistics},
year={2017},
publisher={MIT Press},
url={http://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00287}
}
@inproceedings{noriega2017learning,
title={Learning what to read: Focused machine reading},
author={Noriega-Atala, Enrique and Valenzuela-Escarcega, Marco A and Morrison, Clayton and Surdeanu, Mihai},
booktitle={Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
pages={2895-2900},
year={2017},
url={https://arxiv.org/pdf/1709.00149.pdf}
}
@article{lee2017scaffolding,
title={A scaffolding approach to coreference resolution integrating statistical and rule-based models},
author={Lee, Heeyoung and Surdeanu, Mihai and Jurafsky, Dan},
journal={Natural Language Engineering},
pages={1-30},
year={2017},
publisher={Cambridge University Press},
url={https://www.cambridge.org/core/services/aop-cambridge-core/content/view/042D0D6C6E125EFB939E0F2C2E63152B/S1351324917000109a.pdf/div-class-title-a-scaffolding-approach-to-coreference-resolution-integrating-statistical-and-rule-based-models-div.pdf}
}
@article{hahn2017swanson,
title={Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph},
author={Hahn-Powell, Gus and Valenzuela-Escarcega, Marco A and Surdeanu, Mihai},
journal={Proceedings of ACL 2017, System Demonstrations},
pages={103-108},
year={2017},
url={http://www.aclweb.org/anthology/P17-4018}
}
@inproceedings{enrique2017focused,
title={Focused Reading: Reinforcement Learning for What Documents to Read},
author={Enrique Noriega-Atala and Marco A. Valenzuela-Escarcega and Clayton T. Morrison and Mihai Surdeanu},
booktitle={Proceedings of the Interactive Machine Learning and Semantic Information Retrieval Workshop at ICML, 2017},
year={2017},
url={http://clulab.org/papers/focusedreading2017.pdf}
}
@inproceedings{biocreative6,
title={{Large-scale automated reading with Reach discovers new cancer driving mechanisms}},
author={Valenzuela-Escarcega, Marco A. and Ozgun Babur and Gus Hahn-Powell and Dane Bell and Thomas Hicks and Enrique Noriega-Atala and Xia Wang and Mihai Surdeanu and Emek Demir and Clayton T. Morrison},
pages={201-203},
year={2017},
booktitle={Proceedings of the Sixth BioCreative Challenge Evaluation Workshop},
url={http://clulab.org/papers/biocreative6.pdf}
}
@article{Rains:20182,
author = {Stephen A. Rains and Melanie D. Hingle and Mihai Surdeanu and Dane Bell and Stephen Kobourov},
title = {Effects of Message Framing on Diabetes Screening Attitudes and Behavior},
journal = {Manuscript in preparation},
year = {2018},
url = {http://clulab.org/papers/DiabetesMessageFramingStudyBriefReport.pdf}
}
@inproceedings{lrec2018,
title={Grounding Gradable Adjectives through Crowdsourcing},
author={Sharp, Rebecca and Paul, Mithun and Nagesh, Ajay and Bell, Dane and Surdeanu, Mihai},
booktitle={LREC 2018},
year={2018},
url={http://clulab.org/papers/GroundingGradableAdjectivesthroughCrowdsourcing.pdf}
}
@Article{Rains:2018,
author = {Stephen A. Rains and Melanie D. Hingle and Mihai Surdeanu and Dane Bell and Stephen Kobourov},
title = {A Test of The Risk Perception Attitude Framework as a Message Tailoring Strategy to Promote Diabetes Screening},
journal = {Health Communication},
url = {http://clulab.org/papers/RainsHingleSurdeanuetalHC.pdf},
url_odi = {https://doi.org/10.1080/10410236.2018.1431024},
year = {2018}
}
@InProceedings{jansen2018worldtree,
author = {Peter Jansen and Elizabeth Wainwright and Steven Marmorstein and Clayton T. Morrison},
title = {WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference},
booktitle = {Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC)},
year = {2018},
url = {http://cognitiveai.org/wp-content/uploads/2018/02/jansen_et_al_lrec2018_worldtree_computable_explanation_corpus_8pg_cameraready.pdf},
url_code = {http://cognitiveai.org/explanationbank/}
}
@inproceedings{jansen:akbc2017,
author = {Peter Jansen},
title = {A Study of Automatically Acquiring Explanatory Inference Patterns from Corpora of Explanations: Lessons from Elementary Science Exams},
booktitle = {Proceedings of the 2017 Workshop on Automated Knowledge Base Construction},
series = {AKBC'17},
year = {2017},
url = {http://cognitiveai.org/wp-content/uploads/2017/11/jansen_akbc2017_automatically_acquiring_explanatory_inference_patterns_from_corpora_of_explanations.pdf},
url_data = {http://cognitiveai.org/explanationbank/}
}
@InProceedings{heeyoung2018ecir,
author = {Heeyoung Kwon and Harsh Trivedi and Peter Jansen and Mihai Surdeanu and Niranjan Balasubramanian},
title = {Controlling Information Aggregation for Complex Question Answering},
booktitle = {Proceedings of the 40th European Conference on Information Retrieval (ECIR)},
year = {2018},
url = {http://clulab.org/papers/ecir2018.pdf}
}
@inproceedings{TAG-2018,
author = {Angus G. Forbes and Kristine Lee and Gus Hahn-Powell and Marco A. Valenzuela-Escarcega and Mihai Surdeanu},
title = {Text Annotation Graphs: Annotating Complex Natural Language Phenomena},
booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC'18)},
year = {2018},
month = {May},
address = {Miyazaki, Japan},
publisher = {European Language Resources Association (ELRA)},
url_code = {https://github.com/CreativeCodingLab/TextAnnotationGraphs},
url = {https://arxiv.org/pdf/1711.00529.pdf}
}
@inproceedings{DBLP:conf/naacl/ANMS18,
author = {Ajay Nagesh and
Mihai Surdeanu},
title = {Keep your bearings: Lightly-supervised Information Extraction with Ladder Networks that avoids Semantic Drift},
booktitle = {{NAACL} {HLT} 2018, The 16th Annual Conference of the North American Chapter
of the Association for Computational Linguistics: Human Language Technologies,
New Orleans, Louisiana, USA, Jun 1 - June 6, 2018},
year = {2018},
url = {http://clulab.org/papers/naaclhlt2018.pdf}
}
@inproceedings{whitespaces-identification2018,
title={Scientific Discovery as Link Prediction in Influence and Citation Graphs},
author={Fan Luo and
Marco A. Valenzuela-Escarcega and
Gus Hahn-Powell and
Mihai Surdeanu},
booktitle = {TextGraphs: 12th Workshop on Graph-Based Natural Language Processing},
year={2018},
abstract = {We introduce a machine learning approach for the identification of ``white spaces'' in scientific knowledge. Our approach addresses this task as link prediction over a graph that contains over 2M influence statements such as ``CTCF activates FOXA1'', which were automatically extracted using open-domain machine reading. We model this prediction task using graph-based features extracted from the above influence graph, as well as from a citation graph that captures scientific communities. We evaluated the proposed approach through backtesting. Although the data is heavily unbalanced (50 times more negative examples than positives), our approach predicts which influence links will be discovered in the ``near future'' with a F1 score of 27 points, and a mean average precision of 68\%. },
organization={NAACL},
url_Slides={http://clulab.org/papers/TextGraphs.pdf},
url={http://clulab.org/papers/ScientificDiscoveryasLinkPredictioninInfluenceandCitationGraphs.pdf}
}
@inproceedings{vikasy_ARC_2018,
title={Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge},
author={Yadav, Vikas and Sharp, Rebecca and Surdeanu, Mihai},
booktitle = "Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)",
year={2018},
url = {https://arxiv.org/pdf/1807.01836.pdf}
}
@article{vikasy_ARC_2018,
title={Sanity Check: A Strong Alignment and Information Retrieval Baseline for AI2 Reasoning Challenge},
author={Yadav, Vikas and Sharp, Rebecca and Surdeanu, Mihai},
year={2018},
url = {https://arxiv.org/pdf/1807.01836.pdf}
}
@inproceedings{lrec2018,
title={Lightly-supervised Representation Learning with Global Interpretability},
author={Valenzuela-Escarcega, Marco A and Nagesh, Ajay and Surdeanu, Mihai},
booktitle={arXiv},
year={2018},
url={https://arxiv.org/abs/1805.11545/}
}
@InProceedings{SHARP18.977,
author = {Rebecca Sharp and Mithun Paul and Ajay Nagesh and Dane Bell and Mihai Surdeanu},
title = {Grounding gradable adjectives through crowdsourcing},
booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
year = {2018},
month = {May},
date = {7-12},
location = {Miyazaki, Japan},
editor = {Nicoletta Calzolari and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and H\'{e}l\`{e}ne Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
publisher = {European Language Resources Association (ELRA)},
address = {Paris, France},
isbn = {979-10-95546-00-9},
language = {english},
url = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/977.pdf}
}
@InProceedings{bell2018detecting,
title = {Detecting diabetes risk from social media activity},
author = {Bell, Dane and Laparra, Egoitz and Kousik, Aditya and Ishihara, Terron and Surdeanu, Mihai and Kobourov, Stephen},
booktitle = {Ninth International Workshop on Health Text Mining and Information Analysis (LOUHI)},
year = {2018},
url = {http://clulab.org/papers/louhi2018-t2dmrisk.pdf},
url_Slides = {http://clulab.org/papers/louhi2018-emnlp.pptx}
}
@Article{Zhou:2018,
author = {Jun Zhou and Dane Bell and Sabina Nusrat and Melanie D.\ Hingle and Mihai Surdeanu and Stephen Kobourov},
title = {Calorie estimation from pictures of food: Crowdsourcing study},
journal = {Interactive Journal of Medical Research (IJMR)},
url = {http://clulab.org/papers/Zhou2018.pdf},
doi = {10.2196/ijmr.9359},
year = {2018}
}
@InProceedings{C18-1196,
author = "Nagesh, Ajay
and Surdeanu, Mihai",
title = "An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification",
booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
year = "2018",
publisher = "Association for Computational Linguistics",
pages = "2312-2324",
location = "Santa Fe, New Mexico, USA",
url = "http://aclweb.org/anthology/C18-1196"
}
@Article{ValenzuelaEscarcega2018LargescaleAR,
title = {Large-scale Automated Machine Reading Discovers New
Cancer Driving Mechanisms},
author = {Valenzuela{-}Escarcega, Marco A. and Ozgun Babur and Gus Hahn-Powell and Dane Bell and Thomas Hicks and Enrique Noriega-Atala and Xia Wang and Mihai Surdeanu and Emek Demir and Clayton T. Morrison},
journal = {Database: The Journal of Biological Databases and Curation},
url = {http://clulab.org/papers/escarcega2018.pdf},
doi = {10.1093/database/bay098},
year = {2018}
}
@inproceedings{berger2018emboot,
title={Visual Supervision in Bootstrapped Information Extraction},
author={Berger, Matthew and Nagesh, Ajay and Levine, Joshua A. and Surdeanu, Mihai and Zhang, Hao Helen},
booktitle={Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
year={2018},
url={http://clulab.org/papers/emnlp2018.pdf}
}
@InProceedings{Ebrahimi2018isi,
author = {Mohammadreza Ebrahimi and Mihai Surdeanu and Sagar Samtani and Hsinchun Chen},
title = {Detecting Cyber Threats in Non-English Dark Net Markets: A Cross-Lingual Transfer Learning Approach},
booktitle = {Proceedings of the IEEE Intelligence and Security Informatics Conference (ISI)},
year = {2018},
note = {This paper won the Best Paper Runner-up Award.},
url = {http://clulab.org/papers/isi2018.pdf}
}
@inproceedings{barbosa2019,
title={Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text},
author={Barbosa, George C.G. and Wong, Zechy and Hahn-Powell, Gus and Bell, Dane and Sharp, Rebecca and Valenzuela-Escarcega, Marco A. and Surdeanu, Mihai},
booktitle={Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT): Software Demonstrations},
year={2019},
note={This paper received the Best System Demonstration award},
url={http://clulab.org/papers/NAACL2019_1.pdf}
}
@INPROCEEDINGS {polarity2019,
author = "Enrique Noriega-Atala and Zhengzhong Liang and John A. Bachman and Clayton T. Morrison and Mihai Surdeanu",
title = "Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods",
booktitle = "Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications",
organization={NAACL-HLT},
year = "2019",
url = {http://clulab.org/papers/polarity19.pdf}
}
@inproceedings{fan2019MTre,
title={Semi-Supervised Teacher-Student Architecture for Relation Extraction},
author={Fan Luo and
Ajay Nagesh and
Rebecca Sharp and
Mihai Surdeanu},
booktitle = {Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing},
year={2019},
organization={NAACL-HLT},
url={http://clulab.org/papers/meanteacherre19.pdf}
}
@INPROCEEDINGS {naaclhlt2019-emboot,
author = "Andrew Zupon and Maria Alexeeva and Marco A. Valenzuela-Escarcega and Ajay Nagesh and Mihai Surdeanu",
title = "Lightly Supervised Representation Learning with Global Interpretability",
booktitle = "Proceedings of the 3rd Workshop on Structured Prediction for Natural Language Processing",
year = "2019",
organization = "NAACL-HLT",
url = {http://clulab.org/papers/naaclhlt2019-emboot.pdf}
}
@phdthesis{ghpdiss2018,
author = {Gus Hahn-Powell},
publisher = {The University of Arizona},
year = {2018},
title = {Machine Reading for Scientific Discovery},
url = {https://repository.arizona.edu/handle/10150/630562}
}
@InProceedings{van2019language,
title = {What does the language of foods say about us?},
author = {Van, Hoang and Musa, Ahmad and Chen, Hang and Surdeanu, Mihai and Kobourov, Stephen},
booktitle = {Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI)},
year = {2019},
url = {http://clulab.org/papers/louhi2019.pdf},
url_Slides = {http://clulab.org/papers/louhi2019.pptx}
}
@inproceedings{suntwal-etal-2019-importance,
title = "On the Importance of Delexicalization for Fact Verification",
author = "Suntwal, Sandeep and
Paul, Mithun and
Sharp, Rebecca and
Surdeanu, Mihai",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-1340",
doi = "10.18653/v1/D19-1340",
pages = "3413-3418",
}
@InProceedings{vacareanu2020parsing,
author = {Robert Vacareanu and George C. G. Barbosa and Marco A. Valenzuela-Escarcega and Mihai Surdeanu},
title = {Parsing as Tagging},
booktitle = {Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC)},
year = {2020},
url = {http://clulab.org/papers/pat.pdf}
}
@inproceedings{zheng-tang-2019-edin,
title = "Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder",
author = "Tang, Zheng and Hahn-Powell, Gustave and Surdeanu, Mihai",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
month = jul,
year = "2020",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "http://clulab.org/papers/aclsrw2020-edin.pdf"
}
@inproceedings{vacareanu2020mwe,
title={An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification},
author={Robert Vacareanu and Marco A. Valenzuela-Escarcega and Rebecca Sharp and Mihai Surdeanu},
booktitle={The 28th International Conference on Computational Linguistics in Barcelona (COLING 2020)},
url={http://clulab.org/papers/coling2020-mwe.pdf},
year={2020}
}
@inproceedings{mithun2020modeldis,
title={Data and Model Distillation as a Solution for Domain-transferable Fact Verification},
author={Mithun, Mitch and Suntwal, Sandeep and Surdeanu, Mihai},
booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
url={http://clulab.org/papers/knowledge_disillation.pdf},
year={2021}
}
@inproceedings{liang2021using,
title={Using the Hammer Only on Nails: A Hybrid Method for Representation-based Evidence Retrieval for Question Answering},
author={Liang, Zhengzhong and Zhao, Yiyun and Surdeanu, Mihai},
booktitle={Proceedings of 43rd European Conference on IR Research, ECIR 2021},
url={http://clulab.org/papers/ecir2021-hybrid.pdf},
year={2021}
}
@inproceedings{zheng-tang-2021-edin,
title = "Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractor with an Explanation Decoder",
author = "Tang, Zheng and Surdeanu, Mihai",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: TrustNLP Workshop",
year = "2021",
url = "http://clulab.org/papers/trustNLP2021_edin.pdf"
}
@inproceedings{culnan-etal-2021-ire,
title = "Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection",
author = "Culnan, John and
Park, Seongjin and
Krishnaswamy, Meghavarshini and
Sharp, Rebecca",
booktitle = "Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
month = apr,
year = "2021",
url = "https://www.aclweb.org/anthology/2021.wassa-1.26",
pages = "250--256"
}
@article{Van2021CheapAG,
title={Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading},
author={Hoang Van and Vikas Yadav and M. Surdeanu},
journal={ArXiv},
year={2021},
volume={abs/2106.04134},
url={https://arxiv.org/pdf/2106.04134.pdf}
}
@inproceedings{mithun2021students,
title={Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification},
author={Mithun, Mitch Paul and Suntwal, Sandeep and Surdeanu, Mihai},
booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
pages={6968--6973},
year={2021},
url={https://aclanthology.org/2021.emnlp-main.558.pdf}
}
@inproceedings{van-etal-2021-may-help,
title = "How May {I} Help You? Using Neural Text Simplification to Improve Downstream {NLP} Tasks",
author = "Van, Hoang and
Tang, Zheng and
Surdeanu, Mihai",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.343",
pages = "4074--4080",
abstract = "The general goal of text simplification (TS) is to reduce text complexity for human consumption. In this paper, we investigate another potential use of neural TS: assisting machines performing natural language processing (NLP) tasks. We evaluate the use of neural TS in two ways: simplifying input texts at prediction time and augmenting data to provide machines with additional information during training. We demonstrate that the latter scenario provides positive effects on machine performance on two separate datasets. In particular, the latter use of TS improves the performances of LSTM (1.82{--}1.98{\%}) and SpanBERT (0.7{--}1.3{\%}) extractors on TACRED, a complex, large-scale, real-world relation extraction task. Further, the same setting yields improvements of up to 0.65{\%} matched and 0.62{\%} mismatched accuracies for a BERT text classifier on MNLI, a practical natural language inference dataset.",
}
@misc{noriegaatala2021neural,
title={Neural Architectures for Biological Inter-Sentence Relation Extraction},
author={Enrique Noriega-Atala and Peter M. Lovett and Clayton T. Morrison and Mihai Surdeanu},
year={2021},
eprint={2112.09288},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@article{10.1162/coli_a_00463,
author = {Tang, Zheng and Surdeanu, Mihai},
title = "{It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers}",
journal = {Computational Linguistics},
volume = {49},
number = {1},
pages = {117-156},
year = {2023},
month = {03},
abstract = "{We propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relations that explain the decisions of the relation classifier. We also convert the model outputs to rules to bring global explanations to this approach. This sequence model is trained using a hybrid strategy: supervised, when supervision from pre-existing patterns is available, and semi-supervised otherwise. In the latter situation, we treat the sequence model’s labels as latent variables, and learn the best assignment that maximizes the performance of the relation classifier. We evaluate the proposed approach on the two datasets and show that the sequence model provides labels that serve as accurate explanations for the relation classifier’s decisions, and, importantly, that the joint training generally improves the performance of the relation classifier. We also evaluate the performance of the generated rules and show that the new rules are a great add-on to the manual rules and bring the rule-based system much closer to the neural models.}",
issn = {0891-2017},
doi = {10.1162/coli_a_00463},
url = {https://doi.org/10.1162/coli\_a\_00463},
eprint = {https://direct.mit.edu/coli/article-pdf/49/1/117/2068962/coli\_a\_00463.pdf},
}
@inproceedings{bastan2022-sume,
title={SuMe: A Dataset Towards Summarizing Biomedical Mechanisms},
author={Bastan, Mohaddeseh and Shankar, Nishant and Surdeanu, Mihai and Balasubramanian, Niranjan},
booktitle={Proceedings of the 2022 LREC Conference},
year={2022},
url={http://clulab.org/papers/SuMe_LREC2022.pdf}
}
@inproceedings{bastan2023-structural,
title={NEUROSTRUCTURAL DECODING: Neural Text Generation with Structural Constraints},
author={Bastan, Mohaddeseh and Surdeanu, Mihai and Balasubramanian, Niranjan},
booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)},
year={2023},
url={https://aclanthology.org/2023.acl-long.528.pdf}
}
@inproceedings{rahimi2022bird,
title={Do Transformer Networks Improve the Discovery of Rules from Text?},
author={Rahimi, Mahdi and Surdeanu, Mihai},
booktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
year={2022},
url={http://clulab.org/papers/bird.pdf},
url_Poster={http://clulab.org/papers/can_poster.pdf}
}
@inproceedings{bridgephrases-identification2022,
title={A STEP towards Interpretable Multi-Hop Reasoning: Bridge Phrase Identification and Query Expansion},
author={Fan Luo and
Mihai Surdeanu},
booktitle = {The 13th edition of Language Resources and Evaluation Conference Processing},
year={2022},
abstract = {We propose an unsupervised method for the identification of bridge phrases in multi-hop question answering (QA). Our method
constructs a graph of noun phrases from the question and the available context, and applies the Steiner tree algorithm to identify
the minimal sub-graph that connects all question phrases. Nodes in the sub-graph that bridge loosely-connected or disjoint
subsets of question phrases due to low-strength semantic relations are extracted as bridge phrases. The identified bridge phrases
are then used to expand the query based on the initial question, helping in increasing the relevance of evidence that has little
lexical overlap or semantic relation with the question. Through an evaluation on HotpotQA(Yang et al., 2018), a popular dataset
for multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using
the retrieved sentences; and (c) effective and faithful explanations when answers are provided.},
organization={European Language Resource Association (ELRA)},
url={http://clulab.org/papers/bridgephrases.pdf}
}