Predicting Target Language CCG Supertags Improves Neural Machine Translation

Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch

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


Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) Does explicitly modeling target language syntax help NMT? 2) Is tight integration of words and syntax better than multitask training? We introduce syntactic information in the form of CCG super tags in the decoder, by interleaving the target super tags with the word sequence. Our results on WMT data show that explicitly modeling target syntax improves machine translation quality for German→English, a high-resource pair, and for Romanian→English, a low resource pair and also several syntactic phenomena including prepositional phrase attachment. Furthermore, a tight coupling of words and syntax improves translation quality more than multitask training. By combining target-syntax with adding source-side dependency labels in the embedding layer, we obtain a total improvement of 0.9 BLEU for German→English and 1.2 BLEU for Romanian→English.
Original languageEnglish
Title of host publicationProceedings of the Conference on Machine Translation (WMT), Volume 1: Research Papers
Place of PublicationCopenhagen, Denmark
PublisherAssociation for Computational Linguistics
Number of pages12
ISBN (Print)978-1-945626-10-4
Publication statusPublished - 11 Sep 2017
EventSecond Conference on Machine Translation (WMT) - Copenhagen, Denmark
Duration: 7 Sep 20178 Sep 2017


ConferenceSecond Conference on Machine Translation (WMT)
Abbreviated titleWMT'17
Internet address


Dive into the research topics of 'Predicting Target Language CCG Supertags Improves Neural Machine Translation'. Together they form a unique fingerprint.

Cite this