{"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/the-eval4nlp-shared-task-on-explainable","title":"The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results","arxiv_id":"2110.04392","date":"2021-10-08","proceeding":"EMNLP (Eval4NLP) 2021 11","authors":["Marina Fomicheva","Piyawat Lertvittayakumjorn","Wei Zhao","Steffen Eger","Yang Gao"],"abstract":"In this paper, we introduce the Eval4NLP-2021shared task on explainable quality estimation. Given a source-translation pair, this shared task requires not only to provide a sentence-level score indicating the overall quality of the translation, but also to explain this score by identifying the words that negatively impact translation quality. We present the data, annotation guidelines and evaluation setup of the shared task, describe the six participating systems, and analyze the results. To the best of our knowledge, this is the first shared task on explainable NLP evaluation metrics. Datasets and results are available at https://github.com/eval4nlp/SharedTask2021.","url_abs":"https://arxiv.org/abs/2110.04392v1","url_pdf":"https://arxiv.org/pdf/2110.04392v1.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":"the-eval4nlp-shared-task-on-explainable","repo_url":"https://github.com/eval4nlp/sharedtask2021","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.04392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04392"}},"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/eval4nlp/sharedtask2021","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"d0ccc9061e09490b","entry":"read_sentence_data","repo":"eval4nlp/sharedtask2021","repo_kind":"official","path":"scripts/evaluate.py","file_url":"https://github.com/eval4nlp/sharedtask2021/blob/HEAD/scripts/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0ccc9061e09490b"}},{"code_sha256_prefix":"90299266142c0adb","entry":"read_word_data","repo":"eval4nlp/sharedtask2021","repo_kind":"official","path":"scripts/evaluate.py","file_url":"https://github.com/eval4nlp/sharedtask2021/blob/HEAD/scripts/evaluate.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":"90299266142c0adb"}},{"code_sha256_prefix":"0b2929b5508e97bf","entry":"validate_word_level_data","repo":"eval4nlp/sharedtask2021","repo_kind":"official","path":"scripts/evaluate.py","file_url":"https://github.com/eval4nlp/sharedtask2021/blob/HEAD/scripts/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b2929b5508e97bf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}