DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling

This paper proposes to model the tag sequence of matched words for dynamic integration with extern lexicon. Their method handles each matched words separately by filling unmatched ones with O tag. These sequence tags are filtered and attended by using BERT embeddings as a query.

Comments

  • Overall idea is good.
  • The trie matching in algorithm 1 is not efficient at all.
  • In table 8, hard filtering outperforms soft filtering significantly. Will hard filtering be much slower since you’ll need to remove bad sequences from the batch on CPU?
  • For these works that integrate lexicons, I’m always curious about the baseline performance of max-prefix-matching. At least for NER, max-prefix-matching introduces very low noise.
Rating
  • 5: Transformative: This paper is likely to change our field. It should be considered for a best paper award.
  • 4.5: Exciting: It changed my thinking on this topic. I would fight for it to be accepted.
  • 4: Strong: I learned a lot from it. I would like to see it accepted.
  • 3.5: Leaning positive: It can be accepted more or less in its current form. However, the work it describes is not particularly exciting and/or inspiring, so it will not be a big loss if people don’t see it in this conference.
  • 3: Ambivalent: It has merits (e.g., it reports state-of-the-art results, the idea is nice), but there are key weaknesses (e.g., I didn’t learn much from it, evaluation is not convincing, it describes incremental work). I believe it can significantly benefit from another round of revision, but I won’t object to accepting it if my co-reviewers are willing to champion it.
  • 2.5: Leaning negative: I am leaning towards rejection, but I can be persuaded if my co-reviewers think otherwise.
  • 2: Mediocre: I would rather not see it in the conference.
  • 1.5: Weak: I am pretty confident that it should be rejected.
  • 1: Poor: I would fight to have it rejected.

0 投票人