Lexically Cohesive Neural Machine Translation with Copy Mechanism

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 translat...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-10
Main Authors: Mishra, Vipul, Chu, Chenhui, Arase, Yuki
Format: Article
Language:English
Subjects:
Cohesion
Context
Copying
Machine translation
Translations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422