{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:21:27Z","timestamp":1757618487141,"version":"3.44.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National University Ireland, Galway"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Identifying the relevant information for a user\u2019s query is a difficult task and is considered complex because contextual information may be spread across the document. Approaches, where documents are represented as a series of passages, have been used in the past to attempt to improve the performance of ad-hoc retrieval systems. In this paper, we present our approach of generating a graph from the top returned passages where each node in the graph corresponds to a passage (against a given query) and an edge weight represent a similarity between them. To form the graph, we generated only the edges between the nodes (passages) that belongs to the same document. The core idea of this strategy is to determine some indicator of the documents\u2019 cohesiveness. A graph-based approaches is adopted to calculate the document cohesion. We discuss two different approaches of generating the cohesion score. At first, we only considered the passages within the same document (i.e. inter-passage connectivity) to formulate the graph and to measure the cohesion score. Later, we extend our approach by generating a bipartite graph where we also include query-passage similarity along with the inter-passage similarity to calculate the document cohesion. We compared the cohesion score of relevant (<jats:italic>R<\/jats:italic>) and non-relevant (<jats:italic>NR<\/jats:italic>) documents and illustrate that our passage-based graph approach produce different results for <jats:italic>R<\/jats:italic> and <jats:italic>NR<\/jats:italic> documents. Additionally, we re-ranked the search results and assessed the effectiveness of the system by combining the cohesion score with a document similarity score.<\/jats:p>","DOI":"10.1007\/s42979-025-04014-0","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:36:49Z","timestamp":1752140209000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Finding Document Cohesion through Passage Graph Approach to Re-Rank Search Results"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5238-7345","authenticated-orcid":false,"given":"Ghulam","family":"Sarwar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Colm","family":"O\u2019Riordan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,9]]},"reference":[{"key":"4014_CR1","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s10791-011-9172-x","volume":"15","author":"R Blanco","year":"2012","unstructured":"Blanco R, Lioma C. Graph-based term weighting for information retrieval. Inf Retrieval. 2012;15:54\u201392.","journal-title":"Inf Retrieval"},{"key":"4014_CR2","doi-asserted-by":"crossref","unstructured":"Rousseau F, Vazirgiannis M. Graph-of-word and TW-IDF: new approach to ad hoc IR. In: Proceedings Of The 22nd ACM international conference on information and knowledge management; 2013. p. 59\u201368.","DOI":"10.1145\/2505515.2505671"},{"key":"4014_CR3","doi-asserted-by":"crossref","unstructured":"Li X, Chen E. Graph-based answer passage ranking for question answering. In: 2010 International Conference On Computational Intelligence and Security (CIS); 2010. p. 634\u20138.","DOI":"10.1109\/CIS.2010.144"},{"key":"4014_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1852102.1852104","volume":"28","author":"O Kurland","year":"2010","unstructured":"Kurland O, Lee L. PageRank without hyperlinks: structural reranking using links induced by language models. ACM Trans Inf Syst (TOIS). 2010;28:1\u201338.","journal-title":"ACM Trans Inf Syst (TOIS)"},{"key":"4014_CR5","doi-asserted-by":"crossref","unstructured":"Dkaki T, Mothe J, Truong Q. Passage retrieval using graph vertices comparison. 2007 Third International IEEE Conference On Signal-Image Technologies And Internet-Based System. 2007: 71-76","DOI":"10.1109\/SITIS.2007.82"},{"key":"4014_CR6","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1137\/S0036144502415960","volume":"46","author":"V Blondel","year":"2004","unstructured":"Blondel V, Gajardo A, Heymans M, Senellart P, Van Dooren P. A measure of similarity between graph vertices: applications to synonym extraction and web searching. SIAM Rev. 2004;46:647\u201366.","journal-title":"SIAM Rev"},{"key":"4014_CR7","doi-asserted-by":"crossref","unstructured":"Kurland O, Lee L. Respect my authority! HITS without hyperlinks, utilizing cluster-based language models. In: Proceedings Of The 29th annual international ACM SIGIR conference on research and development in information retrieval; 2006. p. 83\u201390.","DOI":"10.1145\/1148170.1148188"},{"key":"4014_CR8","doi-asserted-by":"crossref","unstructured":"Shah C, Croft W. Evaluating high accuracy retrieval techniques. In: titProceedings Of The 27th annual international ACM SIGIR conference on research and development in information retrieval; 2004. p. 2\u20139.","DOI":"10.1145\/1008992.1008996"},{"key":"4014_CR9","doi-asserted-by":"crossref","unstructured":"Thammasut D, Sornil O. A graph-based information retrieval system. In: 2006 international symposium on communications and information technologies; 2006. p. 743\u20138.","DOI":"10.1109\/ISCIT.2006.339839"},{"key":"4014_CR10","doi-asserted-by":"crossref","unstructured":"Tan J, Wan X, Xiao J. Abstractive document summarization with a graph-based attentional neural model. In: Proceedings Of The 55th annual meeting of The Association For Computational Linguistics (volume 1: long papers); 2017. p. 1171\u201381.","DOI":"10.18653\/v1\/P17-1108"},{"key":"4014_CR11","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s10791-020-09369-x","volume":"23","author":"E Sheetrit","year":"2020","unstructured":"Sheetrit E, Shtok A, Kurland O. A passage-based approach to learning to rank documents. Inf Retr J. 2020;23:159\u201386.","journal-title":"Inf Retr J"},{"key":"4014_CR12","doi-asserted-by":"crossref","unstructured":"Dai Z, Callan J. Context-aware passage term weighting for first stage retrieval. In: Proceedings Of The 43rd international ACM SIGIR conference on research and development in information retrieval, virtual event, China, July 25\u201330, 2020; 2020.","DOI":"10.1145\/3397271.3401204"},{"key":"4014_CR13","unstructured":"Nogueira R, Cho K. Passage Re-ranking with BERT. CoRR. abs\/1901.04085 (2019), arXiv: org\/abs\/1901.04085"},{"key":"4014_CR14","unstructured":"Mitra B, Craswell N. An updated duet model for passage re-ranking. CoRR. arXiv:1903.07666 (2019)."},{"key":"4014_CR15","doi-asserted-by":"crossref","unstructured":"Yulianti E, Chen R, Scholer F, Croft W, Sanderson M. Ranking documents by answer-passage quality. In: The 41st international ACM SIGIR conference on research and development in information retrieval; 2018. p. 335\u201344.","DOI":"10.1145\/3209978.3210028"},{"key":"4014_CR16","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1561\/1500000016","volume":"3","author":"T Liu","year":"2009","unstructured":"Liu T. Learning to rank for information retrieval. Found Trends Inf Retr. 2009;3:225\u2013331 (3).","journal-title":"Found Trends Inf Retr"},{"key":"4014_CR17","doi-asserted-by":"crossref","unstructured":"Kurland O. The cluster hypothesis in information retrieval. In: European conference on information retrieval; 2014. p. 823\u20136.","DOI":"10.1007\/978-3-319-06028-6_105"},{"key":"4014_CR18","doi-asserted-by":"crossref","unstructured":"Voorhees, E. The cluster hypothesis revisited. In: Proceedings Of The 8th annual international ACM SIGIR conference on research and development in information retrieval; 1985. p. 188\u201396.","DOI":"10.1145\/253495.253524"},{"key":"4014_CR19","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.is.2018.02.009","volume":"80","author":"F Benedetti","year":"2019","unstructured":"Benedetti F, Beneventano D, Bergamaschi S, Simonini G. Computing inter-document similarity with context semantic analysis. Inf Syst. 2019;80:136\u201347.","journal-title":"Inf Syst"},{"key":"4014_CR20","unstructured":"Aryal S, Ting K, Washio T, Haffari G. A new simple and effective measure for bag-of-word inter-document similarity measurement. CoRR. arXiv:1902.03402 (2019)."},{"key":"4014_CR21","doi-asserted-by":"crossref","unstructured":"Sheetrit E, Shtok A, Kurland O, Shprincis I. Testing the cluster hypothesis with focused and graded relevance judgments. In: The 41st international ACM SIGIR conference on research and development in information retrieval; 2018. p. 1173\u20136.","DOI":"10.1145\/3209978.3210120"},{"key":"4014_CR22","doi-asserted-by":"crossref","unstructured":"Sheetrit E, Kurland O. Cluster-based focused retrieval. In: Proceedings Of The 28th ACM international conference on information and knowledge management; 2019. p. 2305\u20138.","DOI":"10.1145\/3357384.3358087"},{"key":"4014_CR23","doi-asserted-by":"crossref","unstructured":"Sarwar G, O\u2019Riordan C. A Graph-based approach at passage level to investigate the cohesiveness of documents. In: Proceedings Of The 10th international conference on data science, technology and applications\u2014DATA; 2021. p. 115\u201323.","DOI":"10.5220\/0010619100002993"},{"key":"4014_CR24","doi-asserted-by":"crossref","unstructured":"Callan J. Passage-level evidence in document retrieval. In: Proceedings of the 17th annual international ACM SIGIR conference on research and development in information retrieval; 1994. p. 302\u201310.","DOI":"10.1007\/978-1-4471-2099-5_31"},{"key":"4014_CR25","doi-asserted-by":"crossref","unstructured":"Liu X, Croft W. Passage retrieval based on language models. In: Proceedings of the eleventh international conference on information and knowledge management; 2002. p. 375\u201382.","DOI":"10.1145\/584792.584854"},{"key":"4014_CR26","first-page":"33","volume":"23","author":"M Hearst","year":"1997","unstructured":"Hearst M. TextTiling: segmenting text into multi-paragraph subtopic passages. Comput Linguist. 1997;23:33\u201364.","journal-title":"Comput Linguist"},{"key":"4014_CR27","doi-asserted-by":"crossref","unstructured":"Bendersky M, Kurland O. Utilizing passage-based language models for document retrieval. In: European conference on information retrieval; 2008. p. 162\u201374.","DOI":"10.1007\/978-3-540-78646-7_17"},{"key":"4014_CR28","unstructured":"Jong M, Ri C, Choe H, Hwang C. A method of passage-based document retrieval in question answering system. CoRR. (2015). arXiv:1512.05437"},{"key":"4014_CR29","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/1877766.1877769","volume":"29","author":"E Krikon","year":"2010","unstructured":"Krikon E, Kurland O, Bendersky M. Utilizing inter-passage and inter-document similarities for reranking search results. ACM Trans Inf Syst (TOIS). 2010;29:3.","journal-title":"ACM Trans Inf Syst (TOIS)."},{"key":"4014_CR30","doi-asserted-by":"crossref","unstructured":"Bendersky M, Kurland O. Re-ranking search results using document-passage graphs. In: Proceedings of the 31st annual international ACM SIGIR conference on research and development in information retrieval; 2008. p. 853\u20134.","DOI":"10.1145\/1390334.1390539"},{"key":"4014_CR31","doi-asserted-by":"crossref","unstructured":"Lashkari A, Mahdavi F, Ghomi V. A boolean model in information retrieval for search engines. In: ICIME\u201909. international conference on Information management and engineering; 2009. p. 385\u20139.","DOI":"10.1109\/ICIME.2009.101"},{"key":"4014_CR32","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/0306-4573(94)00052-5","volume":"31","author":"J Zobel","year":"1995","unstructured":"Zobel J, Moffat A, Wilkinson R, Sacks-Davis R. Efficient retrieval of partial documents. Inf Process Manag. 1995;31:361\u201377.","journal-title":"Inf Process Manag"},{"key":"4014_CR33","doi-asserted-by":"crossref","unstructured":"Sarwar G, O\u2019Riordan C, Newell J. Passage level evidence for effective document level retrieval. In: Proceedings of the 9th international joint conference on knowledge discovery, knowledge engineering and knowledge management; 2017. p. 83\u201390.","DOI":"10.5220\/0006502800830090"},{"key":"4014_CR34","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1002\/1532-2890(2000)9999:9999<::AID-ASI1075>3.0.CO;2-#","volume":"52","author":"M Kaszkiel","year":"2001","unstructured":"Kaszkiel M, Zobel J. Effective ranking with arbitrary passages. J Am Society Inf Sci Technol. 2001;52:344\u201364.","journal-title":"J Am Society Inf Sci Technol"},{"key":"4014_CR35","doi-asserted-by":"crossref","unstructured":"Blair D. Information retrieval, 2nd edn. C.J. Van Rijsbergen. London: Butterworths. J Am Soc Inf Sci. 1979.","DOI":"10.1002\/asi.4630300621"},{"key":"4014_CR36","doi-asserted-by":"crossref","unstructured":"Renoust B, Melan\u00e7on G, Viaud M. Measuring group cohesion in document collections. In: Proceedings of the 2013 IEEE\/WIC\/ACM international joint conferences on web intelligence (WI) and intelligent agent technologies (IAT)-Volume 01; 2013. p. 373\u201380.","DOI":"10.1109\/WI-IAT.2013.53"},{"key":"4014_CR37","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1016\/j.ipm.2008.01.003","volume":"44","author":"O Vechtomova","year":"2008","unstructured":"Vechtomova O, Karamuftuoglu M. Lexical cohesion and term proximity in document ranking. Inf Process Manag. 2008;44:1485\u2013502.","journal-title":"Inf Process Manag"},{"key":"4014_CR38","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10115-008-0135-5","volume":"17","author":"V Kandylas","year":"2008","unstructured":"Kandylas V, Upham S, Ungar L. Finding cohesive clusters for analyzing knowledge communities. Knowl Inf Syst. 2008;17:335\u201354.","journal-title":"Knowl Inf Syst"},{"key":"4014_CR39","doi-asserted-by":"crossref","unstructured":"Ai Q, O\u2019Connor B, Croft W. A neural passage model for ad-hoc document retrieval. In: European conference on information retrieval; 2018. p. 537\u201343.","DOI":"10.1007\/978-3-319-76941-7_41"},{"key":"4014_CR40","unstructured":"P\u00e9rez R, Pagola J. An incremental text segmentation by clustering cohesion. In: Kayser C, Montmain J (Eds.) Proceedings of the First Workshop on Human Centered Design for Adaptive Intelligent Systems (HaCDAIS 2010); 2010 Aug 31; Paris, France. Aachen: CEUR-WS.org; 2010. p. 65\u201372. (CEUR Workshop Proceedings; vol. 667)."},{"key":"4014_CR41","volume-title":"The pagerank citation ranking: bringing order to the web","author":"L Page","year":"1999","unstructured":"Page L, Brin S, Motwani R, Winograd T. The pagerank citation ranking: bringing order to the web. Stanford: Stanford InfoLab; 1999."},{"key":"4014_CR42","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1145\/324133.324140","volume":"46","author":"J Kleinberg","year":"1999","unstructured":"Kleinberg J. Authoritative sources in a hyperlinked environment. J ACM (JACM). 1999;46:604\u201332.","journal-title":"J ACM (JACM)"},{"key":"4014_CR43","first-page":"63","volume":"7","author":"H Dang","year":"2007","unstructured":"Dang H, Kelly D, Lin J. Overview of the TREC 2007 question answering track. Trec. 2007;7:63.","journal-title":"Trec."},{"key":"4014_CR44","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.ipm.2008.06.004","volume":"45","author":"J Otterbacher","year":"2009","unstructured":"Otterbacher J, Erkan G, Radev D. Biased LexRank: passage retrieval using random walks with question-based priors. Inf Process Manag. 2009;45:42\u201354.","journal-title":"Inf Process Manag"},{"key":"4014_CR45","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1613\/jair.1523","volume":"22","author":"G Erkan","year":"2004","unstructured":"Erkan G, Radev D. Lexrank: graph-based lexical centrality as salience in text summarization. J Artif Intell Res. 2004;22:457\u201379.","journal-title":"J Artif Intell Res"},{"key":"4014_CR46","doi-asserted-by":"crossref","unstructured":"Cui H, Sun R, Li K, Kan M, Chua T. Question answering passage retrieval using dependency relations. In: Proceedings of the 28th annual international ACM SIGIR conference on research and development in information retrieval; 2005. p. 400\u20137.","DOI":"10.1145\/1076034.1076103"},{"key":"4014_CR47","unstructured":"Kong K, Luk R, Ho K, Chung F. Passage-based retrieval using parameterized fuzzy set operators. In: Methods for information retrieval: ACM SIGIR workshop on mathematical\/formal; 2004."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04014-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04014-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04014-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T02:11:43Z","timestamp":1757211103000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04014-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,9]]},"references-count":47,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["4014"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04014-0","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2025,7,9]]},"assertion":[{"value":"13 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interests to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"613"}}