Combining Input Augmentation and Constrained Decoding for Lexically-Constrained Neural Machine Translation
-
- Chousa Katsuki
- NTT Communication Science Laboratories
-
- Morishita Makoto
- NTT Communication Science Laboratories
-
- Nagata Masaaki
- NTT Communication Science Laboratories
Bibliographic Information
- Other Title
-
- 入力拡張と制約付きデコーディングによる語彙制約付き機械翻訳
Abstract
<p>Lexically constrained machine translation is a task wherein the translation model is required to output translated sentences that contain all specified phrase constraints. In this paper, we propose a method for improving the efficiency of lexically-constrained decoding by extending the input sequence of the model. The results of experiments performed on En↔Ja indicate that the proposed method achieves higher translation accuracy with less computational cost than do the conventional methods. Furthermore, we propose a method for automatically extracting noisy lexical constraints by using the lexical constraint machine translation method. Experiments on Ja→En show that the proposed method can achieve a higher level of accuracy than do general machine translation methods. </p>
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 29 (4), 1052-1081, 2022
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390012954685723648
-
- ISSN
- 21858314
- 13407619
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
-
- Abstract License Flag
- Disallowed