Lexically Cohesive Neural Machine Translation with Copy Mechanism
release_y7ukd7lo5bfp5mh6n2kdiw7qoq
by
Vipul Mishra, Chenhui Chu, Yuki Arase
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) |
2010.05193v1
access all versions, variants, and formats of this works (eg, pre-prints)