Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
13 changed files
with
24,250 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,21 @@ | ||
| Tools for computing distributed representtion of words | ||
| ------------------------------------------------------ | ||
|
|
||
| We provide an implementation of the Continuous Bag-of-Words (CBOW) and the Skip-gram model (SG), as well as several demo scripts. | ||
|
|
||
| Given a text corpus, the word2vec tool learns a vector for every word in the vocabulary using the Continuous | ||
| Bag-of-Words or the Skip-Gram neural network architectures. The user should to specify the following: | ||
| - desired vector dimensionality | ||
| - the size of the context window for either the Skip-Gram or the Continuous Bag-of-Words model | ||
| - training algorithm: hierarchical softmax and / or negative sampling | ||
| - threshold for downsampling the frequent words | ||
| - number of threads to use | ||
| - the format of the output word vector file (text or binary) | ||
|
|
||
| Usually, the other hyper-parameters such as the learning rate do not need to be tuned for different training sets. | ||
|
|
||
| The script demo-word.sh downloads a small (100MB) text corpus from the web, and trains a small word vector model. After the training | ||
| is finished, the user can interactively explore the similarity of the words. | ||
|
|
||
| More information about the scripts is provided at https://code.google.com/p/word2vec/ | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,44 @@ | ||
|
|
||
| Microsoft Visual Studio Solution File, Format Version 12.00 | ||
| # Visual Studio 2013 | ||
| VisualStudioVersion = 12.0.31101.0 | ||
| MinimumVisualStudioVersion = 10.0.40219.1 | ||
| Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Word2Vec.Net", "Word2Vec.Net\Word2Vec.Net.csproj", "{FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}" | ||
| EndProject | ||
| Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Work2VecConsoleApp", "Work2VecConsoleApp\Work2VecConsoleApp.csproj", "{7724C534-6B39-4DA6-92CD-DA2155EE944C}" | ||
| EndProject | ||
| Global | ||
| GlobalSection(SolutionConfigurationPlatforms) = preSolution | ||
| Debug|Any CPU = Debug|Any CPU | ||
| Debug|Mixed Platforms = Debug|Mixed Platforms | ||
| Debug|Win32 = Debug|Win32 | ||
| Release|Any CPU = Release|Any CPU | ||
| Release|Mixed Platforms = Release|Mixed Platforms | ||
| Release|Win32 = Release|Win32 | ||
| EndGlobalSection | ||
| GlobalSection(ProjectConfigurationPlatforms) = postSolution | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Debug|Any CPU.ActiveCfg = Debug|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Debug|Any CPU.Build.0 = Debug|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Debug|Mixed Platforms.ActiveCfg = Debug|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Debug|Mixed Platforms.Build.0 = Debug|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Debug|Win32.ActiveCfg = Debug|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Release|Any CPU.ActiveCfg = Release|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Release|Any CPU.Build.0 = Release|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Release|Mixed Platforms.ActiveCfg = Release|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Release|Mixed Platforms.Build.0 = Release|Any CPU | ||
| {FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}.Release|Win32.ActiveCfg = Release|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Debug|Any CPU.ActiveCfg = Debug|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Debug|Any CPU.Build.0 = Debug|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Debug|Mixed Platforms.ActiveCfg = Debug|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Debug|Mixed Platforms.Build.0 = Debug|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Debug|Win32.ActiveCfg = Debug|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Release|Any CPU.ActiveCfg = Release|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Release|Any CPU.Build.0 = Release|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Release|Mixed Platforms.ActiveCfg = Release|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Release|Mixed Platforms.Build.0 = Release|Any CPU | ||
| {7724C534-6B39-4DA6-92CD-DA2155EE944C}.Release|Win32.ActiveCfg = Release|Any CPU | ||
| EndGlobalSection | ||
| GlobalSection(SolutionProperties) = preSolution | ||
| HideSolutionNode = FALSE | ||
| EndGlobalSection | ||
| EndGlobal |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,36 @@ | ||
| using System.Reflection; | ||
| using System.Runtime.CompilerServices; | ||
| using System.Runtime.InteropServices; | ||
|
|
||
| // General Information about an assembly is controlled through the following | ||
| // set of attributes. Change these attribute values to modify the information | ||
| // associated with an assembly. | ||
| [assembly: AssemblyTitle("Word2Vec.Net")] | ||
| [assembly: AssemblyDescription("")] | ||
| [assembly: AssemblyConfiguration("")] | ||
| [assembly: AssemblyCompany("")] | ||
| [assembly: AssemblyProduct("Word2Vec.Net")] | ||
| [assembly: AssemblyCopyright("Copyright © 2015")] | ||
| [assembly: AssemblyTrademark("")] | ||
| [assembly: AssemblyCulture("")] | ||
|
|
||
| // Setting ComVisible to false makes the types in this assembly not visible | ||
| // to COM components. If you need to access a type in this assembly from | ||
| // COM, set the ComVisible attribute to true on that type. | ||
| [assembly: ComVisible(false)] | ||
|
|
||
| // The following GUID is for the ID of the typelib if this project is exposed to COM | ||
| [assembly: Guid("b2bcc46d-a28b-40a4-a873-f0b1ffe65181")] | ||
|
|
||
| // Version information for an assembly consists of the following four values: | ||
| // | ||
| // Major Version | ||
| // Minor Version | ||
| // Build Number | ||
| // Revision | ||
| // | ||
| // You can specify all the values or you can default the Build and Revision Numbers | ||
| // by using the '*' as shown below: | ||
| // [assembly: AssemblyVersion("1.0.*")] | ||
| [assembly: AssemblyVersion("1.0.0.0")] | ||
| [assembly: AssemblyFileVersion("1.0.0.0")] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| using System.Collections.Generic; | ||
|
|
||
| namespace Word2Vec.Net | ||
| { | ||
| internal class VocubWord | ||
| { | ||
| public long Cn { get; set; } | ||
| public string Word { get; set; } | ||
| public char[] Code { get; set; } | ||
| public char CodeLen { get; set; } | ||
| public int[] Point { get; set; } | ||
| } | ||
| // Used later for sorting by word counts | ||
| internal class VocubComparer : IComparer<VocubWord> | ||
| { | ||
| public int Compare(VocubWord x, VocubWord y) | ||
| { | ||
| if (x == null && y == null) | ||
| return 0; | ||
| if (y == null) return -1; | ||
| if (x == null) return 1; | ||
| return (int)(y.Cn - x.Cn ); | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,56 @@ | ||
| <?xml version="1.0" encoding="utf-8"?> | ||
| <Project ToolsVersion="12.0" DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003"> | ||
| <Import Project="$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props" Condition="Exists('$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props')" /> | ||
| <PropertyGroup> | ||
| <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration> | ||
| <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform> | ||
| <ProjectGuid>{FEFCA2DC-137B-4EEE-A779-0194BDFEBE1F}</ProjectGuid> | ||
| <OutputType>Library</OutputType> | ||
| <AppDesignerFolder>Properties</AppDesignerFolder> | ||
| <RootNamespace>Word2Vec.Net</RootNamespace> | ||
| <AssemblyName>Word2Vec.Net</AssemblyName> | ||
| <TargetFrameworkVersion>v4.5</TargetFrameworkVersion> | ||
| <FileAlignment>512</FileAlignment> | ||
| </PropertyGroup> | ||
| <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' "> | ||
| <DebugSymbols>true</DebugSymbols> | ||
| <DebugType>full</DebugType> | ||
| <Optimize>false</Optimize> | ||
| <OutputPath>bin\Debug\</OutputPath> | ||
| <DefineConstants>DEBUG;TRACE</DefineConstants> | ||
| <ErrorReport>prompt</ErrorReport> | ||
| <WarningLevel>4</WarningLevel> | ||
| <DocumentationFile>bin\Debug\Word2Vec.Net.XML</DocumentationFile> | ||
| </PropertyGroup> | ||
| <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' "> | ||
| <DebugType>pdbonly</DebugType> | ||
| <Optimize>true</Optimize> | ||
| <OutputPath>bin\Release\</OutputPath> | ||
| <DefineConstants>TRACE</DefineConstants> | ||
| <ErrorReport>prompt</ErrorReport> | ||
| <WarningLevel>4</WarningLevel> | ||
| </PropertyGroup> | ||
| <ItemGroup> | ||
| <Reference Include="System" /> | ||
| <Reference Include="System.Core" /> | ||
| <Reference Include="System.Xml.Linq" /> | ||
| <Reference Include="System.Data.DataSetExtensions" /> | ||
| <Reference Include="Microsoft.CSharp" /> | ||
| <Reference Include="System.Data" /> | ||
| <Reference Include="System.Xml" /> | ||
| </ItemGroup> | ||
| <ItemGroup> | ||
| <Compile Include="VocubWord.cs" /> | ||
| <Compile Include="Word2Vec.cs" /> | ||
| <Compile Include="Properties\AssemblyInfo.cs" /> | ||
| <Compile Include="Word2VecBuilder.cs" /> | ||
| </ItemGroup> | ||
| <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" /> | ||
| <!-- To modify your build process, add your task inside one of the targets below and uncomment it. | ||
| Other similar extension points exist, see Microsoft.Common.targets. | ||
| <Target Name="BeforeBuild"> | ||
| </Target> | ||
| <Target Name="AfterBuild"> | ||
| </Target> | ||
| --> | ||
| </Project> |
Oops, something went wrong.