Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework

Генерация ответов в диалоге с использованием поиска руководящих примеров через фреймворк «сопоставление‑к‑генерации»
Wei Bi, Deng Cai, Zhaopeng Tu, Shuming Shi, Yan Wang, Xiaojiang Liu
2019-01-01

dialogue response generationmatching-to-generation frameworkretrieval-augmented generationretrieval-guided dialogue
Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Shuming Shi. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
1
Approach reported in EMNLP-IJCNLP 2019 as a novel way to combine retrieval and generation for dialogue systems
2
Framework improves retrieval-guided dialogue response generation by matching retrieved candidates before generation
3
Method leverages retrieved responses as explicit guidance rather than directly copying them into generated replies
4
Proposes a matching-to-generation framework that uses retrieved dialogue responses to guide generation of new responses

Retrieval-guided dialogue response generation system (matching-to-generation framework)

Effectiveness of a matching-to-generation framework for guiding neural dialogue response generation using retrieved candidate responses

Publication Details
Publication Date
2019-01-01
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Wei Bi
Deng Cai
Zhaopeng Tu
Shuming Shi
Yan Wang
Xiaojiang Liu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat
Make a presentation
100%