Difference between revisions of "Language modeling software"

From ACL Wiki
Jump to: navigation, search
(reorganize, add more LM software)
 
Line 3: Line 3:
 
For languages other than English, see [[List of resources by language]].
 
For languages other than English, see [[List of resources by language]].
  
== Language modeling ==
+
== Language modeling software ==
 +
 
  
 
=== Free software ===
 
=== Free software ===
 
<!-- Please keep this list in alphabetical order -->
 
<!-- Please keep this list in alphabetical order -->
 +
*[http://sourceforge.net/projects/irstlm/ IRSTLM] - Free software for language modeling
 +
*[http://kheafield.com/code/kenlm/ KenLM] - Fast, Free software for language modeling
 +
*[https://code.google.com/p/mitlm/ MITLM] - MIT Language Modeling (MITLM) toolkit
 +
*[http://openfst.cs.nyu.edu/twiki/bin/view/GRM/NGramLibrary OpenGrm NGram] library - Free software for language modeling.  Built on [[OpenFst]].
 +
*[http://sifaka.cs.uiuc.edu/~ylv2/pub/plm/plm.htm Positional Language Model]
 +
*[http://sourceforge.net/projects/randlm/ RandLM] - Free software for randomised language modeling
 +
*[http://vsiivola.github.io/variKN/ VariKN] - Free software for creating, growing and pruning Kneser-Ney smoothed n-gram models.
  
 +
=== Non-Free software ===
 +
<!-- Please keep this list in alphabetical order -->
 
* [https://cmusphinx.svn.sourceforge.net/svnroot/cmusphinx/trunk/cmuclmtk/ cmuclmtk] - CMU-Cambridge Statistical Language Modeling toolkit. Older versions are available [http://www.speech.cs.cmu.edu/SLM/toolkit.html here].
 
* [https://cmusphinx.svn.sourceforge.net/svnroot/cmusphinx/trunk/cmuclmtk/ cmuclmtk] - CMU-Cambridge Statistical Language Modeling toolkit. Older versions are available [http://www.speech.cs.cmu.edu/SLM/toolkit.html here].
 
* [http://www.speech.sri.com/projects/srilm/ SRILM] - The SRI Language Modeling Toolkit. Nitin Madnani has created Perl and Python wrappers, which are available from his [http://www.umiacs.umd.edu/~nmadnani/ homepage].
 
* [http://www.speech.sri.com/projects/srilm/ SRILM] - The SRI Language Modeling Toolkit. Nitin Madnani has created Perl and Python wrappers, which are available from his [http://www.umiacs.umd.edu/~nmadnani/ homepage].
 
* [http://ilk.uvt.nl/wopr/ WOPR] - Memory-based word prediction and language modeling - uses [http://ilk.uvt.nl/timbl TiMBL]. GPL.
 
* [http://ilk.uvt.nl/wopr/ WOPR] - Memory-based word prediction and language modeling - uses [http://ilk.uvt.nl/timbl TiMBL]. GPL.
 +
 +
 +
== Models ==
 +
*[http://www.keithv.com/software/csr/ Language models trained on newswire data]
 +
  
 
[[Category:Software]]
 
[[Category:Software]]
 
[[Category:Resources for English]]
 
[[Category:Resources for English]]

Latest revision as of 18:56, 8 October 2013

Tools and Software for English - Language modeling

For languages other than English, see List of resources by language.

Language modeling software

Free software

  • IRSTLM - Free software for language modeling
  • KenLM - Fast, Free software for language modeling
  • MITLM - MIT Language Modeling (MITLM) toolkit
  • OpenGrm NGram library - Free software for language modeling. Built on OpenFst.
  • Positional Language Model
  • RandLM - Free software for randomised language modeling
  • VariKN - Free software for creating, growing and pruning Kneser-Ney smoothed n-gram models.

Non-Free software

  • cmuclmtk - CMU-Cambridge Statistical Language Modeling toolkit. Older versions are available here.
  • SRILM - The SRI Language Modeling Toolkit. Nitin Madnani has created Perl and Python wrappers, which are available from his homepage.
  • WOPR - Memory-based word prediction and language modeling - uses TiMBL. GPL.


Models