Conversational Search with Random Walks over Entity Graphs

Gustavo Gonçalves, João Magalhães, Jamie Callan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Downloads (Pure)

Abstract

The entities that emerge during a conversation can be used to model topics, but not all entities are equally useful for this task. Modeling the conversation with entity graphs and predicting each entity's centrality in the conversation provides additional information that improves the retrieval of answer passages for the current question. Experiments show that using random walks to estimate entity centrality on conversation entity graphs improves top precision answer passage ranking over competitive transformer-based baselines.
Original languageEnglish
Title of host publicationICTIR 2023
Subtitle of host publicationProceedings of the 2023 ACM SIGIR International Conference on the Theory of Information Retrieval
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages77-85
Number of pages9
ISBN (Print)979-8-4007-0073-6
DOIs
Publication statusPublished - 9 Aug 2023
Event9th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2023 - Taipei, Taiwan, Province of China
Duration: 23 Jul 202323 Jul 2023

Publication series

NameICTIR: Theory of Information Retrieval
PublisherAssociation for Computing Machinery

Conference

Conference9th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2023
Country/TerritoryTaiwan, Province of China
CityTaipei
Period23/07/2323/07/23

Keywords

  • conversational search
  • entity graph
  • named-entities
  • passage retrieval

Fingerprint

Dive into the research topics of 'Conversational Search with Random Walks over Entity Graphs'. Together they form a unique fingerprint.

Cite this