search

neulab / awesome-align

A neural word aligner based on multilingual BERT
https://arxiv.org/abs/2101.08231
BSD 3-Clause "New" or "Revised" License
321 stars 46 forks source link

Is it possible align phrase by phrase, not just word by word? #52

Open fishfree opened 1 year ago

fishfree commented 1 year ago

For many languages, there are lots of unpaired words, but lots of paired phrase.

zdou0830 commented 1 year ago

It's possible as here we first compute subword alignments and then convert them to word alignments, thus we can use the same strategy to convert them to phrase alignments.

lofti198 commented 1 year ago

For many languages, there are lots of unpaired words, but lots of paired phrase.

Which language pair you use?

fishfree commented 1 year ago

@lofti198 For example, English & Chinese.

@zdou0830 Thank you. Then need we manually annotate the gold prase alignment corpus first?

zdou0830 commented 1 year ago

You'll need to do phrase segmentation and use this segmentation during inference. Changing our word-level self-training objective (detail in the paper) to phrase-level self-training objective may also be helpful. If you have gold phrase alignment information, you can also use our model in supervised settings (https://github.com/neulab/awesome-align#supervised-settings) to train the model.