Named-Entity Tagging and Domain adaptation for Better Customized Translation

Named-Entity Tagging and Domain adaptation for Better Customized Translation
Title:
Named-Entity Tagging and Domain adaptation for Better Customized Translation
Other Titles:
Proceedings of the Seventh Named Entities Workshop 2018
DOI:
Keywords:
Publication Date:
20 July 2018
Citation:
Abstract:
Customized translation need pay spe-cial attention to the target domain ter-minology especially the named-entities for the domain. Adding linguistic features to neural machine translation (NMT) has been shown to benefit translation in many studies. In this paper, we further demonstrate that adding named-entity (NE) feature with named-entity recognition (NER) into the source language produces better translation with NMT. Our experiments show that by just including the different NE classes and boundary tags, we can increase the BLEU score by around 1 to 2 points using the standard test sets from WMT2017. We also show that adding NE tags using NER and applying in-domain adaptation can be combined to further improve customized machine translation.
License type:
PublisherCopyrights
Funding Info:
GovTech, Smart Nation Projects
Description:
ISBN:

Files uploaded:

File Size Format Action
nmt-nameentity-paper-acl-news-submitfinal.pdf 304.15 KB PDF Open