Generating Stylistically Consistent Dialog Responses with Transfer Learning

Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi, Kentaro Inui


Abstract
We propose a novel, data-driven, and stylistically consistent dialog response generation system. To create a user-friendly system, it is crucial to make generated responses not only appropriate but also stylistically consistent. For leaning both the properties effectively, our proposed framework has two training stages inspired by transfer learning. First, we train the model to generate appropriate responses, and then we ensure that the responses have a specific style. Experimental results demonstrate that the proposed method produces stylistically consistent responses while maintaining the appropriateness of the responses learned in a general domain.
Anthology ID:
I17-2069
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
408–412
Language:
URL:
https://aclanthology.org/I17-2069
DOI:
Bibkey:
Cite (ACL):
Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi, and Kentaro Inui. 2017. Generating Stylistically Consistent Dialog Responses with Transfer Learning. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 408–412, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Generating Stylistically Consistent Dialog Responses with Transfer Learning (Akama et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/I17-2069.pdf
Note:
 I17-2069.Notes.pdf