{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/attentive-pooling-networks","title":"Attentive Pooling Networks","arxiv_id":"1602.03609","date":"2016-02-11","proceeding":null,"authors":["Cicero dos Santos","Ming Tan","Bing Xiang","Bo-Wen Zhou"],"abstract":"In this work, we propose Attentive Pooling (AP), a two-way attention\nmechanism for discriminative model training. In the context of pair-wise\nranking or classification with neural networks, AP enables the pooling layer to\nbe aware of the current input pair, in a way that information from the two\ninput items can directly influence the computation of each other's\nrepresentations. Along with such representations of the paired inputs, AP\njointly learns a similarity measure over projected segments (e.g. trigrams) of\nthe pair, and subsequently, derives the corresponding attention vector for each\ninput to guide the pooling. Our two-way attention mechanism is a general\nframework independent of the underlying representation learning, and it has\nbeen applied to both convolutional neural networks (CNNs) and recurrent neural\nnetworks (RNNs) in our studies. The empirical results, from three very\ndifferent benchmark tasks of question answering/answer selection, demonstrate\nthat our proposed models outperform a variety of strong baselines and achieve\nstate-of-the-art performance in all the benchmarks.","url_abs":"http://arxiv.org/abs/1602.03609v1","url_pdf":"http://arxiv.org/pdf/1602.03609v1.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":"attentive-pooling-networks","repo_url":"https://github.com/iamwinter/Attentive-Pooling-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"attentive-pooling-networks","repo_url":"https://github.com/winter1997/Attentive-Pooling-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"attentive-pooling-networks","repo_url":"https://github.com/zhaojinglong/Attentive-Pooling-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-semevalcqa","task":"Question Answering","dataset":"SemEvalCQA","model":"AP-CNN","rank_in_archive_order":3,"of":5,"metrics":{"MAP":" 0.771","P@1":"0.755"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"AP-CNN","rank_in_archive_order":16,"of":25,"metrics":{"MAP":"0.6886","MRR":"0.6957"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-yahoocqa","task":"Question Answering","dataset":"YahooCQA","model":"AP-BiLSTM","rank_in_archive_order":4,"of":7,"metrics":{"MRR":"0.731","P@1":"0.568"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-yahoocqa","task":"Question Answering","dataset":"YahooCQA","model":"AP-CNN","rank_in_archive_order":5,"of":7,"metrics":{"MRR":"0.726","P@1":"0.560"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1602.03609","atlas_url":"https://app.syntology.ai/?focus=1602.03609","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1602.03609"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1602.03609\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1602.03609"},"call":"get_concepts_for_paper(arxiv_id=\"1602.03609\")"}],"by_repo":[{"repo":"iamwinter/Attentive-Pooling-Networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"winter1997/Attentive-Pooling-Networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zhaojinglong/Attentive-Pooling-Networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b1fb902ecb9a18b76f7b310001fd5459efa42d92a8c7b3c0b69dcf27e5d8a682","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}