Towards Improving Neural Named Entity Recognition with Gazetteers

This paper trains a tagger (sub-tagger) to predict the BILOU tags generated by gazetteers and concatenates the feature representation of that tagger to a NER tagger. They are able to score 92.75 on CoNLL03.


  • Is the sub-tagger trained separately or jointly with the main tagger?
  • The gazetteers have noting to do with semi Markov conditional random fields. You can concatenate the gazetteer embeddings to any model.
  • The appendix is missing in PDF. It cannot compile in \LaTeX.
  • Gazetteer type mapping table of CoNLL03 is copied from OntoNotes. Not sure why this careless mistake is presented in an ACL paper.
  • Overall quality is very low.
  • 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