BERT with history answer embedding for conversational question answering

Chen Qu, Liu Yang, Minghui Qiu, W. Bruce Croft, Yongfeng Zhang, Mohit Iyyer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Scopus citations

Abstract

Conversational search is an emerging topic in the information retrieval community. One of the major challenges to multi-turn conversational search is to model the conversation history to answer the current question. Existing methods either prepend history turns to the current question or use complicated attention mechanisms to model the history. We propose a conceptually simple yet highly effective approach referred to as history answer embedding. It enables seamless integration of conversation history into a conversational question answering (ConvQA) model built on BERT (Bidirectional Encoder Representations from Transformers). We first explain our view that ConvQA is a simplified but concrete setting of conversational search, and then we provide a general framework to solve ConvQA. We further demonstrate the effectiveness of our approach under this framework. Finally, we analyze the impact of different numbers of history turns under different settings to provide new insights into conversation history modeling in ConvQA.

Original languageEnglish (US)
Title of host publicationSIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages1133-1136
Number of pages4
ISBN (Electronic)9781450361729
DOIs
StatePublished - Jul 18 2019
Event42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019 - Paris, France
Duration: Jul 21 2019Jul 25 2019

Publication series

NameSIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019
Country/TerritoryFrance
CityParis
Period7/21/197/25/19

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Applied Mathematics
  • Software

Fingerprint

Dive into the research topics of 'BERT with history answer embedding for conversational question answering'. Together they form a unique fingerprint.

Cite this