{"url":"/task/document-translation","name":"Document Translation","slug":"document-translation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":47,"papers_with_code":15,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/codexglue","name":"CodeXGLUE","full_name":"","num_papers_in_archive":205},{"url":"/dataset/wmt-2020","name":"WMT 2020","full_name":"","num_papers_in_archive":33},{"url":"/dataset/iwslt2015","name":"IWSLT2015","full_name":"IWSLT2015","num_papers_in_archive":6}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":15,"of":15,"tagged_in_all":47,"items":[{"url":"/paper/codexglue-a-machine-learning-benchmark","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","date":"2021-02-09","arxiv_id":"2102.04664","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/pre-training-via-paraphrasing","title":"Pre-training via Paraphrasing","date":"2020-06-26","arxiv_id":"2006.15020","repositories_listed":2,"syntology":{"n":18,"n_ran":15,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/agent-capability-negotiation-and-binding","title":"Agent Capability Negotiation and Binding Protocol (ACNBP)","date":"2025-06-16","arxiv_id":"2506.13590","repositories_listed":1,"syntology":null},{"url":"/paper/cross-dialect-information-retrieval","title":"Cross-Dialect Information Retrieval: Information Access in Low-Resource and High-Variance Languages","date":"2024-12-17","arxiv_id":"2412.12806","repositories_listed":1,"syntology":null},{"url":"/paper/delta-an-online-document-level-translation","title":"DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory","date":"2024-10-10","arxiv_id":"2410.08143","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/m3t-a-new-benchmark-dataset-for-multi-modal","title":"M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation","date":"2024-06-12","arxiv_id":"2406.08255","repositories_listed":1,"syntology":null},{"url":"/paper/nusawrites-constructing-high-quality-corpora","title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages","date":"2023-09-19","arxiv_id":"2309.10661","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/transdocs-optical-character-recognition-with","title":"TransDocs: Optical Character Recognition with word to word translation","date":"2023-04-15","arxiv_id":"2304.07637","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-context-with-linear-attention-for-1","title":"Modeling Context With Linear Attention for Scalable Document-Level Translation","date":"2022-10-16","arxiv_id":"2210.08431","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-colbert-x","title":"Neural Approaches to Multilingual Information Retrieval","date":"2022-09-03","arxiv_id":"2209.01335","repositories_listed":1,"syntology":null},{"url":"/paper/udaan-machine-learning-based-post-editing","title":"UDAAN: Machine Learning based Post-Editing tool for Document Translation","date":"2022-03-03","arxiv_id":"2203.01644","repositories_listed":1,"syntology":null},{"url":"/paper/transins-document-translation-with-markup","title":"TransIns: Document Translation with Markup Reinsertion","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/capturing-longer-context-for-document-level","title":"Rethinking Document-level Neural Machine Translation","date":"2020-10-18","arxiv_id":"2010.08961","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/clireval-evaluating-machine-translation-as-a","title":"CLIReval: Evaluating Machine Translation as a Cross-Lingual Information Retrieval Task","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/contextual-neural-model-for-translating","title":"Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations","date":"2018-09-02","arxiv_id":"1809.00344","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}