{"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/two-are-better-than-one-an-ensemble-of","title":"Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems","arxiv_id":"1610.07149","date":"2016-10-23","proceeding":null,"authors":["Yiping Song","Rui Yan","Xiang Li","Dongyan Zhao","Ming Zhang"],"abstract":"Open-domain human-computer conversation has attracted much attention in the\nfield of NLP. Contrary to rule- or template-based domain-specific dialog\nsystems, open-domain conversation usually requires data-driven approaches,\nwhich can be roughly divided into two categories: retrieval-based and\ngeneration-based systems. Retrieval systems search a user-issued utterance\n(called a query) in a large database, and return a reply that best matches the\nquery. Generative approaches, typically based on recurrent neural networks\n(RNNs), can synthesize new replies, but they suffer from the problem of\ngenerating short, meaningless utterances. In this paper, we propose a novel\nensemble of retrieval-based and generation-based dialog systems in the open\ndomain. In our approach, the retrieved candidate, in addition to the original\nquery, is fed to an RNN-based reply generator, so that the neural model is\naware of more information. The generated reply is then fed back as a new\ncandidate for post-reranking. Experimental results show that such ensemble\noutperforms each single part of it by a large margin.","url_abs":"http://arxiv.org/abs/1610.07149v1","url_pdf":"http://arxiv.org/pdf/1610.07149v1.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":"two-are-better-than-one-an-ensemble-of","repo_url":"https://github.com/jimth001/Bi-Seq2Seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"two-are-better-than-one-an-ensemble-of","repo_url":"https://github.com/xingyuliuNLP/ResponseEdit_FR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1610.07149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.07149"}},"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/jimth001/Bi-Seq2Seq","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xingyuliuNLP/ResponseEdit_FR","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"793eebcac4d6a149","entry":"copy_list","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"793eebcac4d6a149"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}