{"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/fine-grained-post-training-for-improving","title":"Fine-grained Post-training for Improving Retrieval-based Dialogue Systems","arxiv_id":null,"date":"2021-05-24","proceeding":"NAACL 2021 4","authors":["Janghoon Han","Taesuk Hong","Byoungjae Kim","Youngjoong Ko","Jungyun Seo"],"abstract":"Retrieval-based dialogue systems display an outstanding performance when pre-trained language models are used, which includes bidirectional encoder representations from transformers (BERT). During the multi-turn response selection, BERT focuses on training the relationship between the context with multiple utterances and the response. However, this method of training is insufficient when considering the relations between each utterance in the context. This leads to a problem of not completely understanding the context flow that is required to select a response. To address this issue, we propose a new fine-grained post-training method that reflects the characteristics of the multi-turn dialogue. Specifically, the model learns the utterance level interactions by training every short context-response pair in a dialogue session. Furthermore, by using a new training objective, the utterance relevance classification, the model understands the semantic relevance and coherence between the dialogue utterances. Experimental results show that our model achieves new state-of-the-art with significant margins on three benchmark datasets. This suggests that the fine-grained post-training method is highly effective for the response selection task.","url_abs":"https://aclanthology.org/2021.naacl-main.122","url_pdf":"https://aclanthology.org/2021.naacl-main.122.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":"fine-grained-post-training-for-improving","repo_url":"https://github.com/hanjanghoon/BERT_FP","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conversational-response-selection","task_name":"Conversational Response Selection"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conversational-response-selection-on-douban-1","task":"Conversational Response Selection","dataset":"Douban","model":"BERT-FP","rank_in_archive_order":3,"of":16,"metrics":{"MAP":"0.644","MRR":"0.680","P@1":"0.512","R10@1":"0.324","R10@2":"0.542","R10@5":"0.870"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-e","task":"Conversational Response Selection","dataset":"E-commerce","model":"BERT-FP","rank_in_archive_order":4,"of":15,"metrics":{"R10@1":"0.870","R10@2":"0.956","R10@5":"0.993"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-rrs","task":"Conversational Response Selection","dataset":"RRS","model":"BERT-FP","rank_in_archive_order":1,"of":7,"metrics":{"MAP":"0.702","MRR":"0.712","P@1":"0.543","R10@1":"0.488","R10@2":"0.708","R10@5":"0.927"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-rrs-1","task":"Conversational Response Selection","dataset":"RRS Ranking Test","model":"BERT-FP","rank_in_archive_order":4,"of":4,"metrics":{"NDCG@3":"0.609","NDCG@5":"0.709"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-ubuntu-1","task":"Conversational Response Selection","dataset":"Ubuntu Dialogue (v1, Ranking)","model":"BERT-FP","rank_in_archive_order":4,"of":25,"metrics":{"R10@1":"0.911","R10@2":"0.962","R10@5":"0.994"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"hanjanghoon/BERT_FP","kind":"named_in_paper","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":"7ec44689cd72d6a78e236d372ae64f3b1adf08116e70769b9f4ec527e5a499ae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}