A graph-based approach at passage level to investigate the cohesiveness of documents

Ghulam Sarwar, Colm O'Riordan

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

2 Citations (Scopus)

Abstract

Approaches involving the representation of documents as a series of passages have been used in the past to improve the performance of ad-hoc retrieval systems. In this paper, we represent the top returned passages as a graph with each passage corresponding to a vertex. We connected the vertices (passages) that belongs to the same document to form a graph. The underlying intuition behind this approach is to identify some measure of the cohesiveness of the documents. We introduce a graph-based approach at the passage level to calculate the cohesion score of each document. The scores for both relevant and non-relevant documents are compared, and we illustrate that the cohesion score differs for relevant and non-relevant. Moreover, we also re-ranked the documents by applying the cohesion score with a document similarity score to inspect its impact on the system's performance.

Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Data Science, Technology and Applications, DATA 2021
EditorsChristoph Quix, Slimane Hammoudi, Wil van der Aalst
PublisherSCITEPRESS
Pages115-123
Number of pages9
ISBN (Electronic)9789897585210
DOIs
Publication statusPublished - 2021
Event10th International Conference on Data Science, Technology and Applications, DATA 2021 - Virtual, Online
Duration: 6 Jul 20218 Jul 2021

Publication series

NameProceedings of the 10th International Conference on Data Science, Technology and Applications, DATA 2021

Conference

Conference10th International Conference on Data Science, Technology and Applications, DATA 2021
CityVirtual, Online
Period6/07/218/07/21

Keywords

  • Document cohesion
  • Inter-passage similarity
  • Passage similarity graph
  • Passage-based document retrieval
  • Query difficulty
  • Re-ranking
  • Weighted graph

Fingerprint

Dive into the research topics of 'A graph-based approach at passage level to investigate the cohesiveness of documents'. Together they form a unique fingerprint.

Cite this