Hierarchy-Aware Global Model for Hierarchical Text Classification

Documents are often grouped in a hierarchy where a parent class derives multiple sub-classes. This paper propose a method to model the label hierarchy. They assign weights to the edge of the label hierarchy tree and employ TreeRNN or GCNN to encourage message passing between label embeddings or text representations along this tree.


  • Their method can be viewed as applying existing methods to a new task.
  • Though labels are hierarchical, texts are not. Their title is misleading.
  • No pre-trained encoder is used, implying that they didn’t get improvement with SOTA baselines.
  • The written-up is hard to follow.
  • 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