English

Understanding Learning Dynamics for Neural Machine Translation

Computation and Language 2020-04-07 v1 Machine Learning

Abstract

Despite the great success of NMT, there still remains a severe challenge: it is hard to interpret the internal dynamics during its training process. In this paper we propose to understand learning dynamics of NMT by using a recent proposed technique named Loss Change Allocation (LCA)~\citep{lan-2019-loss-change-allocation}. As LCA requires calculating the gradient on an entire dataset for each update, we instead present an approximate to put it into practice in NMT scenario. %motivated by the lesson from sgd. Our simulated experiment shows that such approximate calculation is efficient and is empirically proved to deliver consistent results to the brute-force implementation. In particular, extensive experiments on two standard translation benchmark datasets reveal some valuable findings.

Keywords

Cite

@article{arxiv.2004.02199,
  title  = {Understanding Learning Dynamics for Neural Machine Translation},
  author = {Conghui Zhu and Guanlin Li and Lemao Liu and Tiejun Zhao and Shuming Shi},
  journal= {arXiv preprint arXiv:2004.02199},
  year   = {2020}
}

Comments

Preprint

R2 v1 2026-06-23T14:39:53.091Z