@inproceedings{83a1f3585cc74f709fb10bc4c3bf4838,
title = "A graph-based approach at passage level to investigate the cohesiveness of documents",
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.",
keywords = "Document cohesion, Inter-passage similarity, Passage similarity graph, Passage-based document retrieval, Query difficulty, Re-ranking, Weighted graph",
author = "Ghulam Sarwar and Colm O'Riordan",
note = "Publisher Copyright: Copyright {\textcopyright} 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved; 10th International Conference on Data Science, Technology and Applications, DATA 2021 ; Conference date: 06-07-2021 Through 08-07-2021",
year = "2021",
doi = "10.5220/0010619101150123",
language = "English",
series = "Proceedings of the 10th International Conference on Data Science, Technology and Applications, DATA 2021",
publisher = "SCITEPRESS",
pages = "115--123",
editor = "Christoph Quix and Slimane Hammoudi and \{van der Aalst\}, Wil",
booktitle = "Proceedings of the 10th International Conference on Data Science, Technology and Applications, DATA 2021",
}