search

allenai / allennlp

An open-source NLP research library, built on PyTorch.
http://www.allennlp.org
Apache License 2.0
11.73k stars 2.24k forks source link

Support for Multilingual Constituency Parser #4493

Open yongzx opened 4 years ago

yongzx commented 4 years ago

Is your feature request related to a problem? Please describe. My feature request is related to the multilingual constituency parsing, where the current constituency parser in the AllenNLP library only works for English and is no longer the SoTA parser.

Describe the solution you'd like The ideal solution is to have a parser such as the implementation of Berkeley Neural Parser with more language support and integration into the AllenNLP pipeline.

Describe alternatives you've considered The use of Berkeley Neural Parser with spaCy for parsing constituents in eleven languages.

Additional context None

epwalsh commented 4 years ago

Hi @yongzx, while this isn't on our roadmap right now, it would be awesome to have. Contributions would be greatly appreciated!

yongzx commented 4 years ago

Would integrate the current Berkeley Neural Parser into AllenNLP pipeline be a useful contribution? Would love to work on it!

matt-gardner commented 4 years ago

Yes, having that model available would be great!

agururajvais commented 3 years ago

Hi @matt-gardner, @epwalsh and @dirkgr, I would like to work on this if @yongzx is not picking this up. :D

yongzx commented 3 years ago

@agururajvais please go ahead!