Extracting Parallel Sentences from Nonparallel Corpora Using Parallel Hierarchical Attention Network
Joint Authors
Zhu, Shaolin
Yang, Yong
Xu, Chun
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-09-01
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
Collecting parallel sentences from nonparallel data is a long-standing natural language processing research problem.
In particular, parallel training sentences are very important for the quality of machine translation systems.
While many existing methods have shown encouraging results, they cannot learn various alignment weights in parallel sentences.
To address this issue, we propose a novel parallel hierarchical attention neural network which encodes monolingual sentences versus bilingual sentences and construct a classifier to extract parallel sentences.
In particular, our attention mechanism structure can learn different alignment weights of words in parallel sentences.
Experimental results show that our model can obtain state-of-the-art performance on the English-French, English-German, and English-Chinese dataset of BUCC 2017 shared task about parallel sentences’ extraction.
American Psychological Association (APA)
Zhu, Shaolin& Yang, Yong& Xu, Chun. 2020. Extracting Parallel Sentences from Nonparallel Corpora Using Parallel Hierarchical Attention Network. Computational Intelligence and Neuroscience،Vol. 2020, no. 2020, pp.1-9.
https://search.emarefa.net/detail/BIM-1138858
Modern Language Association (MLA)
Zhu, Shaolin…[et al.]. Extracting Parallel Sentences from Nonparallel Corpora Using Parallel Hierarchical Attention Network. Computational Intelligence and Neuroscience No. 2020 (2020), pp.1-9.
https://search.emarefa.net/detail/BIM-1138858
American Medical Association (AMA)
Zhu, Shaolin& Yang, Yong& Xu, Chun. Extracting Parallel Sentences from Nonparallel Corpora Using Parallel Hierarchical Attention Network. Computational Intelligence and Neuroscience. 2020. Vol. 2020, no. 2020, pp.1-9.
https://search.emarefa.net/detail/BIM-1138858
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1138858