Projects per year
Abstract
Neural machine translation has recently achieved impressive results, while using little in the way of external linguistic information. In this paper we show that the strong learning capability of neural MT models does not make linguistic features redundant; they can be easily incorporated to provide further improvements in performance. We generalize the embedding layer of the encoder in the attentional encoder–decoder architecture to support the inclusion of arbitrary features, in addition to the baseline word feature. We add morphological features, part-of speech tags, and syntactic dependency labels as input features to English↔German and English→Romanian neural machine translation systems. In experiments on WMT16 training and test sets, we find that linguistic input features improve model quality according to three metrics: perplexity, BLEU and CHRF3. An opensource implementation of our neural MT system is available , as are sample files and configurations.
Original language | English |
---|---|
Title of host publication | Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers |
Place of Publication | Berlin, Germany |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 83-91 |
Number of pages | 9 |
ISBN (Electronic) | 978-1-945626-10-4 |
DOIs | |
Publication status | Published - 12 Aug 2016 |
Event | First Conference on Machine Translation - Berlin, Germany Duration: 11 Aug 2016 → 12 Aug 2016 http://www.statmt.org/wmt16/ |
Conference
Conference | First Conference on Machine Translation |
---|---|
Abbreviated title | WMT16 |
Country/Territory | Germany |
City | Berlin |
Period | 11/08/16 → 12/08/16 |
Internet address |
Fingerprint
Dive into the research topics of 'Linguistic Input Features Improve Neural Machine Translation'. Together they form a unique fingerprint.Projects
- 2 Finished
-
-
HimL: Health in my Language
Haddow, B., Birch-Mayne, A. & Webber, B.
1/02/15 → 31/01/18
Project: Research