{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/180410877","title":"Entity Set Search of Scientific Literature: An Unsupervised Ranking Approach","arxiv_id":"1804.10877","date":"2018-04-29","proceeding":null,"authors":["Jiaming Shen","Jinfeng Xiao","Xinwei He","Jingbo Shang","Saurabh Sinha","Jiawei Han"],"abstract":"Literature search is critical for any scientific research. Different from Web\nor general domain search, a large portion of queries in scientific literature\nsearch are entity-set queries, that is, multiple entities of possibly different\ntypes. Entity-set queries reflect user's need for finding documents that\ncontain multiple entities and reveal inter-entity relationships and thus pose\nnon-trivial challenges to existing search algorithms that model each entity\nseparately. However, entity-set queries are usually sparse (i.e., not so\nrepetitive), which makes ineffective many supervised ranking models that rely\nheavily on associated click history. To address these challenges, we introduce\nSetRank, an unsupervised ranking framework that models inter-entity\nrelationships and captures entity type information. Furthermore, we develop a\nnovel unsupervised model selection algorithm, based on the technique of\nweighted rank aggregation, to automatically choose the parameter settings in\nSetRank without resorting to a labeled validation set. We evaluate our proposed\nunsupervised approach using datasets from TREC Genomics Tracks and Semantic\nScholar's query log. The experiments demonstrate that SetRank significantly\noutperforms the baseline unsupervised models, especially on entity-set queries,\nand our model selection algorithm effectively chooses suitable parameter\nsettings.","url_abs":"http://arxiv.org/abs/1804.10877v1","url_pdf":"http://arxiv.org/pdf/1804.10877v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"180410877","repo_url":"https://github.com/mickeystroller/SetRank","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.10877","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}