This paper presents a Synergized LSTM cell to automatically decide the message flow from both word embeddings and GCN hidden states to better integrate dependency parse tree features for NER. They duplicate an input gate to work in GCN hidden states and that’s all the novel part.
- I actually like this paper because the design is convincing. If an input gate is effective on word embeddings it should also work on GCN hidden states.
- However, the trend of integrating a lot of features (word, char, dep, GCN, etc.) is just not what will be used in production. It’s written for academia papers and it’s not intended for practical purpose. In reality you won’t have in-domain parsers and you can not afford to run lots of feature extractors. Let me make it clear, I hate this part.
- 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.