A Knowledge storage and semantic space alignment Method for Multi-documents dialogue generation

Minjun Zhu, Bin Li, Yixuan Weng, Fei Xia


Abstract
Question Answering (QA) is a Natural Language Processing (NLP) task that can measure language and semantics understanding ability, it requires a system not only to retrieve relevant documents from a large number of articles but also to answer corresponding questions according to documents. However, various language styles and sources of human questions and evidence documents form the different embedding semantic spaces, which may bring some errors to the downstream QA task. To alleviate these problems, we propose a framework for enhancing downstream evidence retrieval by generating evidence, aiming at improving the performance of response generation. Specifically, we take the pre-training language model as a knowledge base, storing documents’ information and knowledge into model parameters. With the Child-Tuning approach being designed, the knowledge storage and evidence generation avoid catastrophic forgetting for response generation. Extensive experiments carried out on the multi-documents dataset show that the proposed method can improve the final performance, which demonstrates the effectiveness of the proposed framework.
Anthology ID:
2022.dialdoc-1.14
Volume:
Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Song Feng, Hui Wan, Caixia Yuan, Han Yu
Venue:
dialdoc
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
130–135
Language:
URL:
https://aclanthology.org/2022.dialdoc-1.14
DOI:
10.18653/v1/2022.dialdoc-1.14
Bibkey:
Cite (ACL):
Minjun Zhu, Bin Li, Yixuan Weng, and Fei Xia. 2022. A Knowledge storage and semantic space alignment Method for Multi-documents dialogue generation. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 130–135, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
A Knowledge storage and semantic space alignment Method for Multi-documents dialogue generation (Zhu et al., dialdoc 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.dialdoc-1.14.pdf
Data
CoQAMultiDoc2DialQuAC