This garbage paper applies a transformer on punctuations to binary-classify the sentence boundary and claims some improvements on their evaluation data. Their model is essentially not different from https://konvens.org/proceedings/2019/papers/KONVENS2019_paper_41.pdf but the authors did not cite it even as a baseline. Instead, the baselines they used (NLTK, SpaCy) are all rule-based which are not usable at all. Their statement “It is therefore unsurprising to find many segmentation errors in existing corpora” is simply wrong, because most treebanks are carefully sentence segmented, but these authors did not mention it.
Comments
- I’m surprised to see such a low quality paper on ACL2021.
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 投票者