{"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/match-tensor-a-deep-relevance-model-for","title":"Match-Tensor: a Deep Relevance Model for Search","arxiv_id":"1701.07795","date":"2017-01-26","proceeding":null,"authors":["Aaron Jaech","Hetunandan Kamisetty","Eric Ringger","Charlie Clarke"],"abstract":"The application of Deep Neural Networks for ranking in search engines may\nobviate the need for the extensive feature engineering common to current\nlearning-to-rank methods. However, we show that combining simple relevance\nmatching features like BM25 with existing Deep Neural Net models often\nsubstantially improves the accuracy of these models, indicating that they do\nnot capture essential local relevance matching signals. We describe a novel\ndeep Recurrent Neural Net-based model that we call Match-Tensor. The\narchitecture of the Match-Tensor model simultaneously accounts for both local\nrelevance matching and global topicality signals allowing for a rich interplay\nbetween them when computing the relevance of a document to a query. On a large\nheld-out test set consisting of social media documents, we demonstrate not only\nthat Match-Tensor outperforms BM25 and other classes of DNNs but also that it\nlargely subsumes signals present in these models.","url_abs":"http://arxiv.org/abs/1701.07795v1","url_pdf":"http://arxiv.org/pdf/1701.07795v1.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":"match-tensor-a-deep-relevance-model-for","repo_url":"https://github.com/cspoh/IRDM2017","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}