Multilingual Translation with Extensible Multilingual Pretraining and Finetuning

This is a follow-up paper of mBART making the following contributions.

  • It shows that finetuning mBART on mixed multilingual data outperforms the bitext one.
  • It demonstrates the possibility to losslessly extend a pretrained model to incorporate more languages by doubling the languages of mBART.
  • They compile popular MT datasets into a benchmark called ML50.


Although the methods are simple they do require efforts to be made possible. It’s also interesting to know that these pre-trained models can be extended without performance loss.

  • 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