{"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/end-to-end-neural-ad-hoc-ranking-with-kernel","title":"End-to-End Neural Ad-hoc Ranking with Kernel Pooling","arxiv_id":"1706.06613","date":"2017-06-20","proceeding":null,"authors":["Chenyan Xiong","Zhuyun Dai","Jamie Callan","Zhiyuan Liu","Russell Power"],"abstract":"This paper proposes K-NRM, a kernel based neural model for document ranking.\nGiven a query and a set of documents, K-NRM uses a translation matrix that\nmodels word-level similarities via word embeddings, a new kernel-pooling\ntechnique that uses kernels to extract multi-level soft match features, and a\nlearning-to-rank layer that combines those features into the final ranking\nscore. The whole model is trained end-to-end. The ranking layer learns desired\nfeature patterns from the pairwise ranking loss. The kernels transfer the\nfeature patterns into soft-match targets at each similarity level and enforce\nthem on the translation matrix. The word embeddings are tuned accordingly so\nthat they can produce the desired soft matches. Experiments on a commercial\nsearch engine's query log demonstrate the improvements of K-NRM over prior\nfeature-based and neural-based states-of-the-art, and explain the source of\nK-NRM's advantage: Its kernel-guided embedding encodes a similarity metric\ntailored for matching query words to document words, and provides effective\nmulti-level soft matches.","url_abs":"http://arxiv.org/abs/1706.06613v1","url_pdf":"http://arxiv.org/pdf/1706.06613v1.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":"end-to-end-neural-ad-hoc-ranking-with-kernel","repo_url":"https://github.com/AdeDZY/K-NRM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"ad-hoc-information-retrieval","task_name":"Ad-Hoc Information Retrieval"},{"task_slug":"document-ranking","task_name":"Document Ranking"},{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.06613","atlas_url":"https://app.syntology.ai/?focus=1706.06613","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}