{"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/semantic-enrichment-of-pretrained-embedding","title":"Semantic Enrichment of Pretrained Embedding Output for Unsupervised IR","arxiv_id":null,"date":"2021-03-24","proceeding":"AAAI-MAKE 2021 3","authors":["Edmund Dervakos","Giorgos Filandrianos","Konstantinos Thomas","Alexios Mandalios","Chrysoula Zerva","Giorgos Stamou"],"abstract":"The rapid growth of scientific literature in the biomedical and clinical domain has significantly com-\r\nplicated the identification of information of interest by researchers as well as other practitioners. More\r\nimportantly, the rapid emergence of new topics and findings, often hinders the performance of super-\r\nvised approaches, due to the lack of relevant annotated data. The global COVID-19 pandemic further\r\nhighlighted the need to query and navigate uncharted ground in the scientific literature in a prompt\r\nand efficient way.\r\nIn this paper we investigate the potential of semantically enhancing deep transformer architectures\r\nusing SNOMED-CT in order to answer user queries in an unsupervised manner. Our proposed system\r\nattempts to filter and re-rank documents related to a query that were initially retrieved using BERT\r\nmodels. To achieve that, we enhance queries and documents with SNOMED-CT concepts and then im-\r\npose filters on concept co-occurrence between them. We evaluate this approach on OHSUMED dataset\r\nand show competitive performance and we also present our approach for adapting such an approach to\r\nfull papers, such as kaggle’s CORD-19 full-text dataset challenge.","url_abs":"https://proceedings.aaai-make.info/AAAI-MAKE-PROCEEDINGS-2021/paper24.pdf","url_pdf":"https://proceedings.aaai-make.info/AAAI-MAKE-PROCEEDINGS-2021/paper24.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":[],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/information-retrieval-on-ohsumed","task":"Information Retrieval","dataset":"Ohsumed","model":"BERT+CONCEPT FILTER","rank_in_archive_order":1,"of":1,"metrics":{"NDCG":"0.25"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}