Open fishfree opened 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.
For many languages, there are lots of unpaired words, but lots of paired phrase.
Which language pair you use?
@lofti198 For example, English & Chinese.
@zdou0830 Thank you. Then need we manually annotate the gold prase alignment corpus first?
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.
For many languages, there are lots of unpaired words, but lots of paired phrase.