Length-constrained Neural Machine Translation using Length Prediction and Perturbation into Length-aware Positional Encoding
-
- Oka Yui
- Nara Institute of Science and Technology Currently with NTT Communication Science Laboratories
-
- Sudoh Katsuhito
- Nara Institute of Science and Technology
-
- Nakamura Satoshi
- Nara Institute of Science and Technology
Abstract
<p>Neural machine translation often suffers from an under-translation problem owing to its limited modeling of the output sequence lengths. In this study, we propose a novel approach to training a Transformer model using length constraints based on length-aware positional encoding (PE). Because length constraints with exact target sentence lengths degrade the translation performance, we add a random perturbation with a uniform distribution within a certain range to the length constraints in the PE during the training. In the inference step, we predicted the output lengths from the input sequences using a length prediction model based on a large-scale pre-trained language model. In Japanese-to-English and English-to-Japanese translation, experimental results show that the proposed perturbation injection improves the robustness of the length prediction errors, particularly within a certain range. </p>
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 28 (3), 778-801, 2021
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390007912125151872
-
- NII Article ID
- 130008088116
-
- ISSN
- 21858314
- 13407619
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed