A Bichannel Transformer with Context Encoding for Document-Driven Conversation Generation in Social Media
Joint Authors
Cai, Yuanyuan
Zuo, Min
Zhang, Qingchuan
Xiong, Haitao
Li, Ke
Source
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-09-17
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
Along with the development of social media on the internet, dialogue systems are becoming more and more intelligent to meet users’ needs for communication, emotion, and social intercourse.
Previous studies usually use sequence-to-sequence learning with recurrent neural networks for response generation.
However, recurrent-based learning models heavily suffer from the problem of long-distance dependencies in sequences.
Moreover, some models neglect crucial information in the dialogue contexts, which leads to uninformative and inflexible responses.
To address these issues, we present a bichannel transformer with context encoding (BCTCE) for document-driven conversation.
This conversational generator consists of a context encoder, an utterance encoder, and a decoder with attention mechanism.
The encoders aim to learn the distributed representation of input texts.
The multihop attention mechanism is used in BCTCE to capture the interaction between documents and dialogues.
We evaluate the proposed BCTCE by both automatic evaluation and human judgment.
The experimental results on the dataset CMU_DoG indicate that the proposed model yields significant improvements over the state-of-the-art baselines on most of the evaluation metrics, and the generated responses of BCTCE are more informative and more relevant to dialogues than baselines.
American Psychological Association (APA)
Cai, Yuanyuan& Zuo, Min& Zhang, Qingchuan& Xiong, Haitao& Li, Ke. 2020. A Bichannel Transformer with Context Encoding for Document-Driven Conversation Generation in Social Media. Complexity،Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1141635
Modern Language Association (MLA)
Cai, Yuanyuan…[et al.]. A Bichannel Transformer with Context Encoding for Document-Driven Conversation Generation in Social Media. Complexity No. 2020 (2020), pp.1-13.
https://search.emarefa.net/detail/BIM-1141635
American Medical Association (AMA)
Cai, Yuanyuan& Zuo, Min& Zhang, Qingchuan& Xiong, Haitao& Li, Ke. A Bichannel Transformer with Context Encoding for Document-Driven Conversation Generation in Social Media. Complexity. 2020. Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1141635
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1141635