{"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/ties-matter-modifying-kendall-s-tau-for","title":"Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration","arxiv_id":"2305.14324","date":"2023-05-23","proceeding":null,"authors":["Daniel Deutsch","George Foster","Markus Freitag"],"abstract":"Kendall's tau is frequently used to meta-evaluate how well machine translation (MT) evaluation metrics score individual translations. Its focus on pairwise score comparisons is intuitive but raises the question of how ties should be handled, a gray area that has motivated different variants in the literature. We demonstrate that, in settings like modern MT meta-evaluation, existing variants have weaknesses arising from their handling of ties, and in some situations can even be gamed. We propose instead to meta-evaluate metrics with a version of pairwise accuracy that gives metrics credit for correctly predicting ties, in combination with a tie calibration procedure that automatically introduces ties into metric scores, enabling fair comparison between metrics that do and do not predict ties. We argue and provide experimental evidence that these modifications lead to fairer ranking-based assessments of metric performance.","url_abs":"https://arxiv.org/abs/2305.14324v2","url_pdf":"https://arxiv.org/pdf/2305.14324v2.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":"ties-matter-modifying-kendall-s-tau-for","repo_url":"https://github.com/google-research/mt-metrics-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ties-matter-modifying-kendall-s-tau-for","repo_url":"https://github.com/thompsonb/mt-metrics-eval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.14324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14324"}},"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/google-research/mt-metrics-eval","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thompsonb/mt-metrics-eval","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"listed":{"samples":10,"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":"8f813973ac3bf112","entry":"Agreement","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/stats.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/stats.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f813973ac3bf112"}},{"code_sha256_prefix":"c6d9433442d834eb","entry":"Flag2TaskArg","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/mtme.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/mtme.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6d9433442d834eb"}},{"code_sha256_prefix":"4fc726dfa5e19ad8","entry":"KendallLike","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/stats.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/stats.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4fc726dfa5e19ad8"}},{"code_sha256_prefix":"aa9cd2664f35166c","entry":"KendallVariants","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/stats.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/stats.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa9cd2664f35166c"}},{"code_sha256_prefix":"9d06f47545662537","entry":"LocalDir","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/data.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d06f47545662537"}},{"code_sha256_prefix":"489ded4bc6b4fc45","entry":"PrintScores","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/mtme.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/mtme.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"489ded4bc6b4fc45"}},{"code_sha256_prefix":"dbb40b5acf49d38d","entry":"ReadDomainScoreFile","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/data.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbb40b5acf49d38d"}},{"code_sha256_prefix":"9f6815894c7d5c54","entry":"ReadScoreFile","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/data.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f6815894c7d5c54"}},{"code_sha256_prefix":"818d955de02710b7","entry":"Score","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/converters/score_mqm.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/converters/score_mqm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"818d955de02710b7"}},{"code_sha256_prefix":"55b7d806d68aaf9d","entry":"tau_optimization","repo":"thompsonb/mt-metrics-eval","repo_kind":"listed","path":"mt_metrics_eval/tau_optimization.py","file_url":"https://github.com/thompsonb/mt-metrics-eval/blob/HEAD/mt_metrics_eval/tau_optimization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55b7d806d68aaf9d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}