This is the NLP Group GitHub Repository.

You will be able to find papers we have discussed, useful links and resources and a summary table of benefits and drawbacks there are to using some of these methodologies here.

Papers

Prior to a paper presentation please add your paper in the papers folder, naming the PDF after its title ( <title.pdf> ) so we have a copy and make sure we do not present the same paper twice.

Don't forget to check the Wiki for videos and references.

Past Papers

Date	Title of paper	Source
2019-01-09	Enriching Word Vectors with Subword Information	aclweb
2019-01-23	Word Mover’s Embedding: From Word2Vec to Document Embedding	aclweb
2019-02-06	Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank	Stanford University
2019-02-20	Deep contextualized word representations	arxiv
2019-03-06	Efficient Estimation of Word Representations in Vector Space	arxiv
2019-03-20	Distributed Representations of Words and Phrases and their Compositionality	arxiv
2019-06-26	Distributed Representations of Sentences and Documents	Stanford University
2019-07-24	Latent Dirichlet Allocation	Stanford
2019-07-31	Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec	arxiv
2019-09-18	GloVe: Global Vectors for Word Representation	Stanford University
2019-10-03	Algorithms for Non-negative Matrix Factorization	paper
2019-10-23	Effective Approaches to Attention-based Neural Machine Translation	arxiv
2019-11-21	Attention Is All You Need	arxiv
2020-02-12	Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks	arxiv
2020-02-26	XLNet: Generalized Autoregressive Pretraining for Language Understanding	arxiv

Future papers

• CNN Understanding Convolutional Neural Networks for Text Classification (CNN paper; source: aclweb)
• LSTM An LSTM Approach to Short Text Sentiment Classification with Word Embeddings (LSTM paper; source: aclweb)
• eLmo (revisit) Deep contextualized word representations (ELMo paper; source: arxiv)
• Bert BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (Bert paper; source: arxiv)
• Severn
• On the dimensionality of Word Embeddings (how many dimensions are required?)
• Visualizing Data using t-SNE (source: Journal Machine Learning Research)
• Google Universal Sentence Embedding (Universal Sentence encoder; source: Google)