This paper utilizes lots of fancy staff to train an end-to-end KGQA system. These include a differentiable KG and corresponding multi-hop inference. They enumerate all spans from the question to create entity candidates and match it with KB entities using string matching. Their embeddings are averaged using candidate weights and trained together with the QA objective.
Comments
- In section 2, where did you define e_j?
- In section 3.3, it’s bad to jump into the detail without an overall description of why you need this likelihood.
- The writing is just so bad.
- The idea is not novel at all. It should be forwarded to the demo track.
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 投票人