{"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/sequential-matching-network-a-new","title":"Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots","arxiv_id":"1612.01627","date":"2016-12-06","proceeding":"ACL 2017 7","authors":["Yu Wu","Wei Wu","Chen Xing","Ming Zhou","Zhoujun Li"],"abstract":"We study response selection for multi-turn conversation in retrieval-based\nchatbots. Existing work either concatenates utterances in context or matches a\nresponse with a highly abstract context vector finally, which may lose\nrelationships among utterances or important contextual information. We propose\na sequential matching network (SMN) to address both problems. SMN first matches\na response with each utterance in the context on multiple levels of\ngranularity, and distills important matching information from each pair as a\nvector with convolution and pooling operations. The vectors are then\naccumulated in a chronological order through a recurrent neural network (RNN)\nwhich models relationships among utterances. The final matching score is\ncalculated with the hidden states of the RNN. An empirical study on two public\ndata sets shows that SMN can significantly outperform state-of-the-art methods\nfor response selection in multi-turn conversation.","url_abs":"http://arxiv.org/abs/1612.01627v2","url_pdf":"http://arxiv.org/pdf/1612.01627v2.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":"sequential-matching-network-a-new","repo_url":"https://github.com/MarkWuNLP/MultiTurnResponseSelection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"sequential-matching-network-a-new","repo_url":"https://github.com/xiaobaicxy/SMN_Multi_Turn_Response_Selection_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"sequential-matching-network-a-new","repo_url":"https://github.com/yangliuy/NeuralResponseRanking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"conversational-response-selection","task_name":"Conversational Response Selection"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[{"slug":"douban","name":"Douban","full_name":"Douban Conversation Corpus"},{"slug":"douban-conversation-corpus","name":"Douban Conversation Corpus","full_name":"Douban Conversation Corpus"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/conversational-response-selection-on-douban-1","task":"Conversational Response Selection","dataset":"Douban","model":"SMN","rank_in_archive_order":16,"of":16,"metrics":{"MAP":"0.529","MRR":"0.569","P@1":"0.397","R10@1":"0.233","R10@2":"0.396","R10@5":"0.724"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-e","task":"Conversational Response Selection","dataset":"E-commerce","model":"SMN","rank_in_archive_order":15,"of":15,"metrics":{"R10@1":"0.453","R10@2":"0.654","R10@5":"0.886"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-rrs","task":"Conversational Response Selection","dataset":"RRS","model":"SMN","rank_in_archive_order":7,"of":7,"metrics":{"MAP":"0.487","MRR":"0.501","P@1":"0.309","R10@1":"0.281","R10@2":"0.442","R10@5":"0.723"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-ubuntu-1","task":"Conversational Response Selection","dataset":"Ubuntu Dialogue (v1, Ranking)","model":"SMN","rank_in_archive_order":22,"of":25,"metrics":{"R10@1":"0.726","R10@2":"0.822","R10@5":"0.960","R2@1":"0.926"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.01627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01627"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MarkWuNLP/MultiTurnResponseSelection","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaobaicxy/SMN_Multi_Turn_Response_Selection_Pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangliuy/NeuralResponseRanking","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bcfc9e8b905d3ef1","entry":"rank_crossentropy_loss","repo":"yangliuy/NeuralResponseRanking","repo_kind":"listed","path":"matchzoo/losses/rank_losses.py","file_url":"https://github.com/yangliuy/NeuralResponseRanking/blob/HEAD/matchzoo/losses/rank_losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcfc9e8b905d3ef1"}},{"code_sha256_prefix":"ddc9d8a2cabd27e1","entry":"rank_hinge_loss","repo":"yangliuy/NeuralResponseRanking","repo_kind":"listed","path":"matchzoo/losses/rank_losses.py","file_url":"https://github.com/yangliuy/NeuralResponseRanking/blob/HEAD/matchzoo/losses/rank_losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddc9d8a2cabd27e1"}},{"code_sha256_prefix":"3d063b0c90233541","entry":"serialize","repo":"yangliuy/NeuralResponseRanking","repo_kind":"listed","path":"matchzoo/losses/rank_losses.py","file_url":"https://github.com/yangliuy/NeuralResponseRanking/blob/HEAD/matchzoo/losses/rank_losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d063b0c90233541"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}