Compositional Representation of Morphologically-Rich Input for Neural Machine Translation

Duygu Ataman, Marcello Federico

[How to correct problems with metadata yourself]


Abstract
Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed segmenting words into sub-word units and performing translation at the sub-lexical level. However, statistical word segmentation methods have recently shown to be prone to morphological errors, which can lead to inaccurate translations. In this paper, we propose to overcome this problem by replacing the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity. We test our approach in a low-resource setting with five languages from different morphological typologies, and under different composition assumptions. By training NMT to compose word representations from character n-grams, our approach consistently outperforms (from 1.71 to 2.48 BLEU points) NMT learning embeddings of statistically generated sub-word units.
Anthology ID:
P18-2049
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
305–311
Language:
URL:
https://aclanthology.org/P18-2049
DOI:
10.18653/v1/P18-2049
Bibkey:
Cite (ACL):
Duygu Ataman and Marcello Federico. 2018. Compositional Representation of Morphologically-Rich Input for Neural Machine Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 305–311, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Compositional Representation of Morphologically-Rich Input for Neural Machine Translation (Ataman & Federico, ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/P18-2049.pdf
Poster:
 P18-2049.Poster.pdf