{"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/on-measuring-context-utilization-in-document","title":"On Measuring Context Utilization in Document-Level MT Systems","arxiv_id":"2402.01404","date":"2024-02-02","proceeding":null,"authors":["Wafaa Mohammed","Vlad Niculae"],"abstract":"Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware evaluation, such as contrastive methods, only measure translation accuracy on words that need context for disambiguation. Such measures cannot reveal whether the translation model uses the correct supporting context. We propose to complement accuracy-based evaluation with measures of context utilization. We find that perturbation-based analysis (comparing models' performance when provided with correct versus random context) is an effective measure of overall context utilization. For a finer-grained phenomenon-specific evaluation, we propose to measure how much the supporting context contributes to handling context-dependent discourse phenomena. We show that automatically-annotated supporting context gives similar conclusions to human-annotated context and can be used as alternative for cases where human annotations are not available. Finally, we highlight the importance of using discourse-rich datasets when assessing context utilization.","url_abs":"https://arxiv.org/abs/2402.01404v1","url_pdf":"https://arxiv.org/pdf/2402.01404v1.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":"on-measuring-context-utilization-in-document","repo_url":"https://github.com/wafaa014/context-utilization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.01404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01404"}},"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":"deterministic:regex_extraction","url":"https://github.com/Wafaa014/context-utilization","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ZurichNLP/ContraPro","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"found_in_text":{"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":4,"samples":[{"code_sha256_prefix":"b83486ca6125a529","entry":"count_errors","repo":"ZurichNLP/ContraPro","repo_kind":"found_in_text","path":"evaluate.py","file_url":"https://github.com/ZurichNLP/ContraPro/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b83486ca6125a529"}},{"code_sha256_prefix":"d4192f5e85770fdd","entry":"find_version","repo":"Wafaa014/context-utilization","repo_kind":"official","path":"fairseq/release_utils.py","file_url":"https://github.com/Wafaa014/context-utilization/blob/HEAD/fairseq/release_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4192f5e85770fdd"}},{"code_sha256_prefix":"8b884fdc3e1f18c8","entry":"get_scores","repo":"ZurichNLP/ContraPro","repo_kind":"found_in_text","path":"evaluate.py","file_url":"https://github.com/ZurichNLP/ContraPro/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b884fdc3e1f18c8"}},{"code_sha256_prefix":"26da4f92ba56e785","entry":"label_smoothed_nll_loss","repo":"Wafaa014/context-utilization","repo_kind":"official","path":"contextual-mt/contextual_mt/attn_reg_loss.py","file_url":"https://github.com/Wafaa014/context-utilization/blob/HEAD/contextual-mt/contextual_mt/attn_reg_loss.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"code_sha256_prefix":"23b62d01c270ed68","entry":"load_contrastive","repo":"Wafaa014/context-utilization","repo_kind":"official","path":"contextual-mt/contextual_mt/docmt_contrastive_eval.py","file_url":"https://github.com/Wafaa014/context-utilization/blob/HEAD/contextual-mt/contextual_mt/docmt_contrastive_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23b62d01c270ed68"}},{"code_sha256_prefix":"44b6e8848744468f","entry":"get_next_version","repo":"Wafaa014/context-utilization","repo_kind":"official","path":"fairseq/release_utils.py","file_url":"https://github.com/Wafaa014/context-utilization/blob/HEAD/fairseq/release_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44b6e8848744468f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}