{"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/fine-tuned-machine-translation-metrics","title":"Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains","arxiv_id":"2402.18747","date":"2024-02-28","proceeding":null,"authors":["Vilém Zouhar","Shuoyang Ding","Anna Currey","Tatyana Badeka","Jenyuan Wang","Brian Thompson"],"abstract":"We introduce a new, extensive multidimensional quality metrics (MQM) annotated dataset covering 11 language pairs in the biomedical domain. We use this dataset to investigate whether machine translation (MT) metrics which are fine-tuned on human-generated MT quality judgements are robust to domain shifts between training and inference. We find that fine-tuned metrics exhibit a substantial performance drop in the unseen domain scenario relative to metrics that rely on the surface form, as well as pre-trained metrics which are not fine-tuned on MT quality judgments.","url_abs":"https://arxiv.org/abs/2402.18747v2","url_pdf":"https://arxiv.org/pdf/2402.18747v2.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-tuned-machine-translation-metrics","repo_url":"https://github.com/amazon-science/bio-mqm-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.18747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18747"}},"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/amazon-science/bio-mqm-dataset","reach":null}],"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":0,"samples":[{"code_sha256_prefix":"79fd3d4cc3316e33","entry":"get_error","repo":"amazon-science/bio-mqm-dataset","repo_kind":"official","path":"metrics_domain_adaptation/scripts/02-data/04a-get_mqm_bio.py","file_url":"https://github.com/amazon-science/bio-mqm-dataset/blob/HEAD/metrics_domain_adaptation/scripts/02-data/04a-get_mqm_bio.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79fd3d4cc3316e33"}},{"code_sha256_prefix":"b0687524fbebfa93","entry":"sanitize","repo":"amazon-science/bio-mqm-dataset","repo_kind":"official","path":"metrics_domain_adaptation/scripts/02-data/04a-get_mqm_bio.py","file_url":"https://github.com/amazon-science/bio-mqm-dataset/blob/HEAD/metrics_domain_adaptation/scripts/02-data/04a-get_mqm_bio.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0687524fbebfa93"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}