Dynamic Graph Reasoning for Conversational Open-Domain Question Answering

Yongqi Li, Wenjie Li, Liqiang Nie

Research output: Journal article publicationJournal articleAcademic researchpeer-review

1 Citation (Scopus)

Abstract

In recent years, conversational agents have provided a natural and convenient access to useful information in people's daily life, along with a broad and new research topic, conversational question answering (QA). On the shoulders of conversational QA, we study the conversational open-domain QA problem, where users' information needs are presented in a conversation and exact answers are required to extract from the Web. Despite its significance and value, building an effective conversational open-domain QA system is non-trivial due to the following challenges: (1) precisely understand conversational questions based on the conversation context; (2) extract exact answers by capturing the answer dependency and transition flow in a conversation; and (3) deeply integrate question understanding and answer extraction. To address the aforementioned issues, we propose an end-to-end Dynamic Graph Reasoning approach to Conversational open-domain QA (DGRCoQA for short). DGRCoQA comprises three components, i.e., a dynamic question interpreter (DQI), a graph reasoning enhanced retriever (GRR), and a typical Reader, where the first one is developed to understand and formulate conversational questions while the other two are responsible to extract an exact answer from the Web. In particular, DQI understands conversational questions by utilizing the QA context, sourcing from predicted answers returned by the Reader, to dynamically attend to the most relevant information in the conversation context. Afterwards, GRR attempts to capture the answer flow and select the most possible passage that contains the answer by reasoning answer paths over a dynamically constructed context graph. Finally, the Reader, a reading comprehension model, predicts a text span from the selected passage as the answer. DGRCoQA demonstrates its strength in the extensive experiments conducted on a benchmark dataset. It significantly outperforms the existing methods and achieves the state-of-the-art performance.

Original languageEnglish
Article number82
Pages (from-to)1-24
JournalACM Transactions on Information Systems
Volume40
Issue number4
DOIs
Publication statusPublished - Oct 2022

Keywords

  • Conversational question answering
  • open-domain question answering

ASJC Scopus subject areas

  • Information Systems
  • Business, Management and Accounting(all)
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Dynamic Graph Reasoning for Conversational Open-Domain Question Answering'. Together they form a unique fingerprint.

Cite this