Neural Machine Translation Techniques for Named Entity Transliteration

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Transliterating named entities from one language into another can be approached as neural machine translation (NMT) problem, for which we use deep attentional RNN encoder-decoder models. To build a strong transliteration system, we apply well-established techniques from NMT, such as dropout regularization, model ensembling, rescoring with right-to-left models, and back-translation. Our submission to the NEWS 2018 Shared Task on Named Entity Transliteration ranked first in several tracks
Original languageEnglish
Title of host publicationProceedings of the Seventh Named Entities Workshop
PublisherAssociation for Computational Linguistics (ACL)
Number of pages6
Publication statusPublished - 2018
EventNEWS 2018: The Seventh Named Entities Workshop - Melbourne, Australia
Duration: 20 Jul 2018 → …


WorkshopNEWS 2018: The Seventh Named Entities Workshop
Abbreviated titleNEWS 2018
Period20/07/18 → …
Internet address

Cite this