0

Paying Attention to Multi-Word Expressions in Neural Machine Translation

Experiments improve neural machine translation of multi-word expressions by augmenting training corpora with automatically extracted MWE candidates and aligned sentences.

Year
2017
Venue
MTSummit 2017 9
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/1710.06313v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Processing of multi-word expressions (MWEs) is a known problem for any natural language processing task. Even neural machine translation (NMT) struggles to overcome it. This paper presents results of experiments on investigating NMT attention allocation to the MWEs and improving automated translation of sentences that contain MWEs in English->Latvian and English->Czech NMT systems. Two improvement strategies were explored -(1) bilingual pairs of automatically extracted MWE candidates were added to the parallel corpus used to train the NMT system, and (2) full sentences containing the automatically extracted MWE candidates were added to the parallel corpus. Both approaches allowed to increase automated evaluation results. The best result - 0.99 BLEU point increase - has been reached with the first approach, while with the second approach minimal improvements achieved. We also provide open-source software and tools used for MWE extraction and alignment inspection.

Authors

2