[Corpora-List] English verb stemmer/lemmatizer

Jon Dehdari jonsafari at ling.ohio-state.edu
Thu May 31 18:53:17 CEST 2012


For lemmatizing English, the XTAG project has a flat TSV-style list of words with their corresponding lemmas, parts-of-speech, and other features: ftp://ftp.cis.upenn.edu/pub/xtag/morph-1.5/morph-1.5.tar.gz in the file data/morph_english.flat .

The file is licensed under the GPL. TreeTagger uses this file in their project.

Cheers, -Jon Dehdari

On Thu, May 31, 2012 at 02:18:52PM +0430, Mohammad Sadegh Rasooli wrote:
> Dear researchers,
>
> For a project on semantic analysis of Persian verbs using bilingual
> corpora, I want to know what are available English verb
> stemmers/lemmatizers?
>
> I want an open-source tool with the ability of converting English verb
> form to their lemmas ("is going"/"has gone"/"goes"/"go", etc ->"to
> go").
>
>
>
> Best
>
> Mohammad Sadegh Rasooli
>
> Dadegan Research Group, Tehran, Iran: [1]http://dadegan.ir/en
>
> [2]sites.google.com/site/rasoolims/
>
> References
>
> 1. http://dadegan.ir/en
> 2. http://sites.google.com/site/rasoolims/


> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora



More information about the Corpora mailing list