This paper applies logical neural networks (LNN) to entity linking. Due to the powerful LNN, their approach can seamlessly integrate rules and SOTA neural models to obtain benefits from emsembling. On 2 out of 3 datasets, they outperformed previous SOTA, the BLINK system.
- Overall quality is good, especially the motivation is good. You can have good interpretability without losing accuracy.
- I’m not familiar with LNN but their introduction is just about right.
- I expect they gave a more intuitive showcase of interpretability rather than the bare tree-like figure. But well, they used up all 9 pages, they could put it into the appendix anyway.
- 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.