TODAY: Hotel Booking Dialogue Translator
The DCU-Huawei Chinese-English Dialogue Translator is designed to be a real-time, semantics-enhanced, task-oriented machine translation system. The novel contributions are:
- bilingual discourse corpus construction and domain adaptation regarding spoken languages;
- task-oriented named entity (NE) definition and a hybrid strategy for NE recognition and translation; and
- a novel grounded semantic method for dialogue understanding and task-order management.
This system is a case-study demo which can efficiently and accurately assist customers and agents in different languages to reach an agreement in a dialogue for the hotel booking task. All the detailed description are described in this paper:
- Longyue Wang, Jinhua Du, Liangyou Li, Zhaopeng Tu, Andy Way, Qun Liu. 2017. Semantics-Enhanced Task-Oriented Dialogue Translation: A Case Study on Hotel Booking. IJCNLP 2017. [pdf] [bitex]
- Longyue Wang, Xiaojun Zhang, Zhaopeng Tu, Andy Way, Qun Liu. 2016. The Automatic Construction of Discourse Corpus for Dialogue Translation. LREC 2016. [pdf] [bitex] [slides]
Please acknowledge with appropriate citation in any publication or presentation containing research results obtained in whole or in part through the use of the DCU-Huawei Chinese-English Dialogue Translator.
The video of our demo is shown as follows:
This work is supported by the Science Foundation of Ireland (SFI) ADAPT project (Grant No.:13/RC/2106), and partly supported by the DCU-Huawei Joint Project (Grant No.:201504032-A (DCU), YB2015090061 (Huawei)).
Related pattent has been delivered.
If you have any question about this system, please contact us via email.