{"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/investigating-evaluation-of-open-domain","title":"Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References","arxiv_id":"1907.10568","date":"2019-07-24","proceeding":"WS 2019 9","authors":["Prakhar Gupta","Shikib Mehri","Tiancheng Zhao","Amy Pavel","Maxine Eskenazi","Jeffrey P. Bigham"],"abstract":"The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation. Existing metrics have been shown to correlate poorly with human judgement, particularly in open-domain dialog. One alternative is to collect human annotations for evaluation, which can be expensive and time consuming. To demonstrate the effectiveness of multi-reference evaluation, we augment the test set of DailyDialog with multiple references. A series of experiments show that the use of multiple references results in improved correlation between several automatic metrics and human judgement for both the quality and the diversity of system output.","url_abs":"https://arxiv.org/abs/1907.10568v2","url_pdf":"https://arxiv.org/pdf/1907.10568v2.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":"investigating-evaluation-of-open-domain","repo_url":"https://github.com/prakharguptaz/multirefeval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"investigating-evaluation-of-open-domain","repo_url":"https://github.com/seungguini/multiref_eval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dialogue-evaluation","task_name":"Dialogue Evaluation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"open-domain-dialog","task_name":"Open-Domain Dialog"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1907.10568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10568"}},"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/prakharguptaz/multirefeval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seungguini/multiref_eval","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"fdb73e92e8e71135","entry":"clean_split_sentence","repo":"prakharguptaz/multirefeval","repo_kind":"official","path":"Code/score_multiref.py","file_url":"https://github.com/prakharguptaz/multirefeval/blob/HEAD/Code/score_multiref.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fdb73e92e8e71135"}},{"code_sha256_prefix":"adf64d9f13c821c6","entry":"load_json","repo":"prakharguptaz/multirefeval","repo_kind":"official","path":"Code/score_multiref.py","file_url":"https://github.com/prakharguptaz/multirefeval/blob/HEAD/Code/score_multiref.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"adf64d9f13c821c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}