This paper introduces a human annotated dataset ENTSUM for controllable summarization focusing on named entities. This dataset is rather small, containing only 693 documents. It’s annotated in 4 steps:
- rank salient entities
- select salient sentences for selected entities
- select sentences for the summary given entities
- write abstractive summary given selected sentences.
- The treatment of NER is quite rough. You can use better NER tools and entity linking tools too.
- Don’t think any of the baseline models is designed for entities. They must be overfitting such a small dataset. Maybe the authors should consider some few-shot learning methods.
- 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.