This paper proposes to use pointer networks to predict the spans of aspect and opinion for Aspect Sentiment Triplet Extraction. Their pointer network is made of a BiLSTM with 2 MLPs to predict start and end offsets.
The approach section is not intuitive. Lots of details are missing and the authors should not really put them into appendix.
- How do you predict the numbers of Aspect-Opinion-Sentiment triplets?
- How do you embed the dependency tree features per each token?
Given the massive number of questions left even after several rounds of reading, I’d suggest this paper to be revised for another round.
- 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.