Feng, Xiaocheng and Feng, Zhangyin and Zhao, Wanlong and Zou, Nan and Qin, Bing and Liu, Ting (2019) Improved Neural Machine Translation with POS-Tagging Through Joint Decoding. In: Artificial Intelligence for Communications and Networks. First EAI International Conference, AICON 2019, Harbin, China, May 25–26, 2019, Proceedings, Part I.
32698.pdf
Download (344kB)
Abstract
In this paper, we improve the performance of neural machine translation (NMT) with shallow syntax (e.g., POS tag) of target language, which has better accuracy and latency than deep syntax such as dependency parsing. We present three NMT decoding models (independent decoder, gates shared decoder and fully shared decoder) to jointly predict target word and POS tag sequences. Experiments on Chinese-English and German-English translation tasks show that the fully shared decoder can acquire the best performance, which increases the BLEU score by 1.4 and 2.25 points respectively compared with the attention-based NMT model.
| Item Type: | Conference or Workshop Item (UNSPECIFIED) |
|---|---|
| Date Deposited: | 04 Mar 2026 12:13 |
| Last Modified: | 20 Nov 2026 11:46 |
| URI: | https://eprints.eai.eu/id/eprint/23448 |
