search

glample / tagger

Named Entity Recognition Tool
Apache License 2.0
1.16k stars 426 forks source link

Pretrained word embedding #83

Closed HAWLYQ closed 5 years ago

HAWLYQ commented 6 years ago

@glample Hi, in your paper, it was mentioned that you observed significant improvements using pretrained word embeddings. Could you share your pretrained English word embedding with me?

glample commented 6 years ago

Hi,

Yes, you can find them here: https://github.com/glample/tagger/issues/44

enricoversino commented 5 years ago

Hi. I've tested your embeddings and were great. Could you share pretarained italian and french word embeddings?

glample commented 5 years ago

Hi,

I never trained embeddings on these languages, but you can have a look at the fastText embeddings, they should work very well for NER: https://fasttext.cc/docs/en/crawl-vectors.html

sbmaruf commented 5 years ago

@glample I recently used your embeddings. your skip-n-gram embeddings given here are better than fasttext common-crawl vectors except the vectors for dutch. in case of fasttext, dutch pretrained embeddings gives around 85.75f1 score where skip-n-gram gives around 81.**

enricoversino commented 5 years ago

Thanks

From: Guillaume Lample Sent: Friday, May 24, 2019 3:11 AM To: glample/tagger Cc: Enrico Versino ; Manual Subject: Re: [glample/tagger] Pretrained word embedding (#83)

Hi,

I never trained embeddings on these languages, but you can have a look at the fastText embeddings, they should work very well for NER: https://fasttext.cc/docs/en/crawl-vectors.html

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.