HackerPapers

arXiv:1902.07282cs.CL

Semantic Neural Machine Translation using AMR

Linfeng Song, Daniel Gildea, Yue Zhang, Zhiguo Wang, Jinsong Su

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. On the other hand, little work has been done on leveraging semantics for neural machine translation (NMT). In this work, we study the usefulness of AMR (short for abstract meaning representation) on NMT. Experiments on a standard English-to-German dataset show that incorporating AMR as additional knowledge can significantly improve a strong attention-based sequence-to-sequence neural translation model.

arXiv comments
Transaction of ACL 2019
Journal reference
Transactions of the Association for Computational Linguistics, 7, pages19-31, 2019
DOI
doi:10.1162/tacl_a_00252
Subjects
cs.CLComputation and Language cs.AIArtificial Intelligence

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from May 2020 to May 2020.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. Symbolic mathematics finally yields to neural networks 1 comment

    • It looks like they go from tree -> sequence via prefix notation. I'm curious why Lample decided on this seq2seq approach when it seems that there might be models which could be more naturally applied to the tree structure directly [1, 2] [1] https://arxiv.org/abs/1902.07282 (an…

      orange3xchickenView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.