File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Lexical-Constraint-Aware Neural Machine Translation via Data Augmentation
Title | Lexical-Constraint-Aware Neural Machine Translation via Data Augmentation |
---|---|
Authors | |
Keywords | Natural Language Processing: Machine Translation Natural Language Processing: Natural Language Processing |
Issue Date | 2021 |
Publisher | International Joint Conference on Artificial Intelligence. The Journal's web site is located at https://www.ijcai.org/past_proceedings |
Citation | Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20) and the 17th Pacific Rim International Conference on Artificial Intelligence (PRICAI), Yokohama, Japan, 7-15 January 2021, p. 3587-3593 How to Cite? |
Abstract | Leveraging lexical constraint is extremely significant in domain-specific machine translation and interactive machine translation. Previous studies mainly focus on extending beam search algorithm or augmenting the training corpus by replacing source phrases with the corresponding target translation. These methods either suffer from the heavy computation cost during inference or depend on the quality of the bilingual dictionary pre-specified by user or constructed with statistical machine translation. In response to these problems, we present a conceptually simple and empirically effective data augmentation approach in lexical constrained neural machine translation. Specifically, we make constraint-aware training data by first randomly sampling the phrases of the reference as constraints, and then packing them together into the source sentence with a separation symbol. Extensive experiments on several language pairs demonstrate that our approach achieves superior translation results over the existing systems, improving translation of constrained sentences without hurting the unconstrained ones. |
Description | Main track - Natural Language Processing |
Persistent Identifier | http://hdl.handle.net/10722/288226 |
ISSN | 2020 SCImago Journal Rankings: 0.649 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, G | - |
dc.contributor.author | Chen, Y | - |
dc.contributor.author | Wang, Y | - |
dc.contributor.author | Li, VOK | - |
dc.date.accessioned | 2020-10-05T12:09:45Z | - |
dc.date.available | 2020-10-05T12:09:45Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20) and the 17th Pacific Rim International Conference on Artificial Intelligence (PRICAI), Yokohama, Japan, 7-15 January 2021, p. 3587-3593 | - |
dc.identifier.issn | 1045-0823 | - |
dc.identifier.uri | http://hdl.handle.net/10722/288226 | - |
dc.description | Main track - Natural Language Processing | - |
dc.description.abstract | Leveraging lexical constraint is extremely significant in domain-specific machine translation and interactive machine translation. Previous studies mainly focus on extending beam search algorithm or augmenting the training corpus by replacing source phrases with the corresponding target translation. These methods either suffer from the heavy computation cost during inference or depend on the quality of the bilingual dictionary pre-specified by user or constructed with statistical machine translation. In response to these problems, we present a conceptually simple and empirically effective data augmentation approach in lexical constrained neural machine translation. Specifically, we make constraint-aware training data by first randomly sampling the phrases of the reference as constraints, and then packing them together into the source sentence with a separation symbol. Extensive experiments on several language pairs demonstrate that our approach achieves superior translation results over the existing systems, improving translation of constrained sentences without hurting the unconstrained ones. | - |
dc.language | eng | - |
dc.publisher | International Joint Conference on Artificial Intelligence. The Journal's web site is located at https://www.ijcai.org/past_proceedings | - |
dc.relation.ispartof | International Joint Conference on Artificial Intelligence. Proceedings | - |
dc.subject | Natural Language Processing: Machine Translation | - |
dc.subject | Natural Language Processing: Natural Language Processing | - |
dc.title | Lexical-Constraint-Aware Neural Machine Translation via Data Augmentation | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Li, VOK: vli@eee.hku.hk | - |
dc.identifier.authority | Li, VOK=rp00150 | - |
dc.identifier.doi | 10.24963/ijcai.2020/496 | - |
dc.identifier.hkuros | 315140 | - |
dc.identifier.spage | 3587 | - |
dc.identifier.epage | 3593 | - |
dc.publisher.place | United States | - |
dc.identifier.eisbn | 9780999241165 | - |
dc.identifier.issnl | 1045-0823 | - |