Convolution-Enhanced Bilingual Recursive Neural Network for Bilingual Semantic Modeling

Jinsong Su, Biao Zhang, Deyi Xiong, Ruochen Li, Jianmin Yin

[How to correct problems with metadata yourself]

Abstract
Estimating similarities at different levels of linguistic units, such as words, sub-phrases and phrases, is helpful for measuring semantic similarity of an entire bilingual phrase. In this paper, we propose a convolution-enhanced bilingual recursive neural network (ConvBRNN), which not only exploits word alignments to guide the generation of phrase structures but also integrates multiple-level information of the generated phrase structures into bilingual semantic modeling. In order to accurately learn the semantic hierarchy of a bilingual phrase, we develop a recursive neural network to constrain the learned bilingual phrase structures to be consistent with word alignments. Upon the generated source and target phrase structures, we stack a convolutional neural network to integrate vector representations of linguistic units on the structures into bilingual phrase embeddings. After that, we fully incorporate information of different linguistic units into a bilinear semantic similarity model. We introduce two max-margin losses to train the ConvBRNN model: one for the phrase structure inference and the other for the semantic similarity model. Experiments on NIST Chinese-English translation tasks demonstrate the high quality of the generated bilingual phrase structures with respect to word alignments and the effectiveness of learned semantic similarities on machine translation.
Anthology ID:
C16-1289
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
3071–3081
Language:
URL:
https://aclanthology.org/C16-1289
DOI:
Bibkey:
Cite (ACL):
Jinsong Su, Biao Zhang, Deyi Xiong, Ruochen Li, and Jianmin Yin. 2016. Convolution-Enhanced Bilingual Recursive Neural Network for Bilingual Semantic Modeling. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3071–3081, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Convolution-Enhanced Bilingual Recursive Neural Network for Bilingual Semantic Modeling (Su et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/C16-1289.pdf
PDF Search