Improving sequence-to-sequence learning via optimal transport

Liqun Chen, Yizhe Zhang, Ruiyi Zhang, Chenyang Tao, Zhe Gan, Haichao Zhang, Bai Li, Dinghan Shen, Changyou Chen, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE). However, standard MLE training considers a word-level objective, predicting the next word given the previous ground-truth partial sentence. This procedure focuses on modeling local syntactic patterns, and may fail to capture long-range semantic structure. We present a novel solution to alleviate these issues. Our approach imposes global sequence-level guidance via new supervision based on optimal transport, enabling the overall characterization and preservation of semantic features. We further show that this method can be understood as a Wasserstein gradient flow trying to match our model to the ground truth sequence distribution. Extensive experiments are conducted to validate the utility of the proposed approach, showing consistent improvements over a wide variety of NLP tasks, including machine translation, abstractive text summarization, and image captioning.
Original languageEnglish (US)
Title of host publication7th International Conference on Learning Representations, ICLR 2019
PublisherInternational Conference on Learning Representations, ICLR
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Dive into the research topics of 'Improving sequence-to-sequence learning via optimal transport'. Together they form a unique fingerprint.

Cite this