Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy

Seong Ku Kang, Shivam Agarwal, Bowen Jin, Dongha Lee, Hwanjo Yu, Jiawei Han

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

Abstract

Document retrieval has greatly benefited from the advancements of large-scale pre-trained language models (PLMs). However, their effectiveness is often limited in theme-specific applications for specialized areas or industries, due to unique terminologies, incomplete contexts of user queries, and specialized search intents. To capture the theme-specific information and improve retrieval, we propose to use a corpus topical taxonomy, which outlines the latent topic structure of the corpus while reflecting user-interested aspects. We introduce ToTER (Topical Taxonomy Enhanced Retrieval) framework, which identifies the central topics of queries and documents with the guidance of the taxonomy, and exploits their topical relatedness to supplement missing contexts. As a plug-and-play framework, ToTER can be flexibly employed to enhance various PLM-based retrievers. Through extensive quantitative, ablative, and exploratory experiments on two real-world datasets, we ascertain the benefits of using topical taxonomy for retrieval in theme-specific applications and demonstrate the effectiveness of ToTER.

Original languageEnglish (US)
Title of host publicationWWW 2024 - Proceedings of the ACM Web Conference
PublisherAssociation for Computing Machinery
Pages1497-1508
Number of pages12
ISBN (Electronic)9798400701719
DOIs
StatePublished - May 13 2024
Event33rd ACM Web Conference, WWW 2024 - Singapore, Singapore
Duration: May 13 2024May 17 2024

Publication series

NameWWW 2024 - Proceedings of the ACM Web Conference

Conference

Conference33rd ACM Web Conference, WWW 2024
Country/TerritorySingapore
CitySingapore
Period5/13/245/17/24

Keywords

  • document retrieval
  • theme-specific application
  • topical taxonomy

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Fingerprint

Dive into the research topics of 'Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy'. Together they form a unique fingerprint.

Cite this