Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder

Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Yonatan Belinkov, Stephan Vogel


Abstract
End-to-end training makes the neural machine translation (NMT) architecture simpler, yet elegant compared to traditional statistical machine translation (SMT). However, little is known about linguistic patterns of morphology, syntax and semantics learned during the training of NMT systems, and more importantly, which parts of the architecture are responsible for learning each of these phenomenon. In this paper we i) analyze how much morphology an NMT decoder learns, and ii) investigate whether injecting target morphology in the decoder helps it to produce better translations. To this end we present three methods: i) simultaneous translation, ii) joint-data learning, and iii) multi-task learning. Our results show that explicit morphological information helps the decoder learn target language morphology and improves the translation quality by 0.2–0.6 BLEU points.
Anthology ID:
I17-1015
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
142–151
Language:
URL:
https://aclanthology.org/I17-1015
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/I17-1015.pdf