This paper presents one of the winner solutions of CoNLL 2020 shared task, Cross-Framework Meaning Representation Parsing (MRP 2020). Their system called PERIN is essentially a tagger that predicts at least one parsing decision per each token and per each hidden states in parallel. These decisions include:
- Will this token become a node or part of a node?
- How to transform this node to a node label?
- Which node will this token be anchored to?
- I didn’t completely digested all the essences of this paper but so far I can tell it’s a good paper.
- The way they deal with permutation-invarant loss is very elegant.
- Lots of tricks are applied to polish their system.
- Their ranking is very competitive. With the bug fixed, they could be ranked top in this competition.
- I’d definitely read their codes and get back to this paper. It’s worth reading again.
- 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.