{"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/uncertainty-aware-machine-translation","title":"Uncertainty-Aware Machine Translation Evaluation","arxiv_id":"2109.06352","date":"2021-09-13","proceeding":"Findings (EMNLP) 2021 11","authors":["Taisiya Glushkova","Chrysoula Zerva","Ricardo Rei","André F. T. Martins"],"abstract":"Several neural-based metrics have been recently proposed to evaluate machine translation quality. However, all of them resort to point estimates, which provide limited information at segment level. This is made worse as they are trained on noisy, biased and scarce human judgements, often resulting in unreliable quality predictions. In this paper, we introduce uncertainty-aware MT evaluation and analyze the trustworthiness of the predicted quality. We combine the COMET framework with two uncertainty estimation methods, Monte Carlo dropout and deep ensembles, to obtain quality scores along with confidence intervals. We compare the performance of our uncertainty-aware MT evaluation methods across multiple language pairs from the QT21 dataset and the WMT20 metrics task, augmented with MQM annotations. We experiment with varying numbers of references and further discuss the usefulness of uncertainty-aware quality estimation (without references) to flag possibly critical translation mistakes.","url_abs":"https://arxiv.org/abs/2109.06352v2","url_pdf":"https://arxiv.org/pdf/2109.06352v2.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":"uncertainty-aware-machine-translation","repo_url":"https://github.com/Unbabel/COMET","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"uncertainty-aware-machine-translation","repo_url":"https://github.com/deep-spin/ua_comet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"monte-carlo-dropout","method_name":"Monte Carlo Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.06352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06352"}},"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/Unbabel/COMET","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deep-spin/ua_comet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"bc589f40704cf78a","entry":"average_pooling","repo":"deep-spin/ua_comet","repo_kind":"official","path":"comet/models/utils.py","file_url":"https://github.com/deep-spin/ua_comet/blob/HEAD/comet/models/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc589f40704cf78a"}},{"code_sha256_prefix":"b0b39e3b4affdd63","entry":"build_activation","repo":"deep-spin/ua_comet","repo_kind":"official","path":"comet/modules/activations.py","file_url":"https://github.com/deep-spin/ua_comet/blob/HEAD/comet/modules/activations.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0b39e3b4affdd63"}},{"code_sha256_prefix":"490410c5af6ef847","entry":"mask_fill","repo":"deep-spin/ua_comet","repo_kind":"official","path":"comet/models/utils.py","file_url":"https://github.com/deep-spin/ua_comet/blob/HEAD/comet/models/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"490410c5af6ef847"}},{"code_sha256_prefix":"b211e3cd0942a18f","entry":"max_pooling","repo":"deep-spin/ua_comet","repo_kind":"official","path":"comet/models/utils.py","file_url":"https://github.com/deep-spin/ua_comet/blob/HEAD/comet/models/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b211e3cd0942a18f"}},{"code_sha256_prefix":"48d39f3e15bed9c4","entry":"swish","repo":"deep-spin/ua_comet","repo_kind":"official","path":"comet/modules/activations.py","file_url":"https://github.com/deep-spin/ua_comet/blob/HEAD/comet/modules/activations.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"48d39f3e15bed9c4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}