Work

Open-Domain Conversational Question Answering with Historical Answers

Year: 2022

Type: conference-paper

Abstract: Open-domain conversational question answering can be viewed as two tasks: passage retrieval and conversational question answering, where the former relies on selecting candidate passages from a large corpus and the latter requires better understanding of a question with contexts to predict the answers.This paper proposes ConvADR-QA that leverages historical answers to boost retrieval performance and further achieves better answering performance.Our experiments on the benchmark dataset, OR-QuAC, demonstrate that our model outperforms existing baselines in both extractive and generative reader settings, well justifying the effectiveness of historical answers for opendomain conversational question answering.1

DOI: 10.18653/v1/2022.findings-aacl.30

Authors: Hung-Chieh Fang, Kuo-Han Hung, Chen-Wei Huang, Yun-Nung Chen

Institution: National Taiwan University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funder: Ministry of Science and Technology, Taiwan

Awards: Unsupervised Knowledge Acquisition for Deep Language and Dialogue Processing and Interactions( V ), Advanced Technologies for Resource-Constrained Deep Learning( Iv )

OpenAlex ID: W4404783045