Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Translating pro-drop languages with reconstruction models

Wang, Longyue orcid logoORCID: 0000-0002-9062-6183, Tu, Zhaopeng, Shi, Shuming, Zhang, Tong, Graham, Yvette and Liu, Qun orcid logoORCID: 0000-0002-7000-1792 (2018) Translating pro-drop languages with reconstruction models. In: 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), 2 - 7 Feb 2018, New Orleans, LA, USA. ISBN 978-1-57735-800-8

Abstract
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. To date, very little attention has been paid to the dropped pronoun (DP) problem within neural machine translation (NMT). In this work, we propose a novel reconstruction-based approach to alleviating DP translation problems for NMT models. Firstly, DPs within all source sentences are automatically annotated with parallel information extracted from the bilingual training corpus. Next, the annotated source sentence is reconstructed from hidden representations in the NMT model. With auxiliary training objectives, in the terms of reconstruction scores, the parameters associated with the NMT model are guided to produce enhanced hidden representations that are encouraged as much as possible to embed annotated DP information. Experimental results on both Chinese-English and Japanese-English dialogue translation tasks show that the proposed approach significantly and consistently improves translation performance over a strong NMT baseline, which is directly built on the training data annotated with DPs.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Neural Machine Translation; Pro-Drop Language; Dropped Pronoun; Reconstruction Model; Dialogue
Subjects:Computer Science > Artificial intelligence
Computer Science > Computational linguistics
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI 2018). . Association for the Advancement of Artificial Intelligence. ISBN 978-1-57735-800-8
Publisher:Association for the Advancement of Artificial Intelligence
Official URL:https://www.aaai.org/ocs/index.php/AAAI/AAAI18/pap...
Copyright Information:© 2018, Association for the Advancement of Artificial Intelligence
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland, SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund
ID Code:23122
Deposited On:03 Apr 2019 09:33 by Yvette Graham . Last Modified 06 Mar 2020 09:47
Documents

Full text available as:

[thumbnail of wangetal18-trans.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
494kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record