Lexically Cohesive Neural Machine Translation with Copy Mechanism release_y7ukd7lo5bfp5mh6n2kdiw7qoq

by Vipul Mishra, Chenhui Chu, Yuki Arase

Released as a article .

2020  

Abstract

Lexically cohesive translations preserve consistency in word choices in document-level translation. We employ a copy mechanism into a context-aware neural machine translation model to allow copying words from previous translation outputs. Different from previous context-aware neural machine translation models that handle all the discourse phenomena implicitly, our model explicitly addresses the lexical cohesion problem by boosting the probabilities to output words consistently. We conduct experiments on Japanese to English translation using an evaluation dataset for discourse translation. The results showed that the proposed model significantly improved lexical cohesion compared to previous context-aware models.
In text/plain format

Archived Files and Locations

application/pdf  583.2 kB
file_fo5ptwuexrerbcjybyrt5kz5pi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-10-11
Version   v1
Language   en ?
arXiv  2010.05193v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: cc0538dc-b882-4686-81e9-c6302598efae
API URL: JSON