{"url":"/task/parallel-corpus-mining","name":"Parallel Corpus Mining","slug":"parallel-corpus-mining","description_markdown":"Mining a corpus of bilingual sentence pairs that are translations of each other.","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":13,"papers_with_code":8,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/aslg-pc12","name":"ASLG-PC12","full_name":"English-ASL Gloss Parallel Corpus 2012","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/data-mining","name":"Data Mining"}],"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":8,"of":8,"tagged_in_all":13,"items":[{"url":"/paper/massively-multilingual-sentence-embeddings","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","date":"2018-12-26","arxiv_id":"1812.10464","repositories_listed":13,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":4}},{"url":"/paper/margin-based-parallel-corpus-mining-with","title":"Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings","date":"2018-11-03","arxiv_id":"1811.01136","repositories_listed":9,"syntology":null},{"url":"/paper/paracrawl-web-scale-acquisition-of-parallel","title":"ParaCrawl: Web-Scale Acquisition of Parallel Corpora","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/bilingual-corpus-mining-and-multistage-fine","title":"Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts","date":"2023-11-07","arxiv_id":"2311.03696","repositories_listed":1,"syntology":null},{"url":"/paper/uscore-an-effective-approach-to-fully","title":"USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation","date":"2022-02-21","arxiv_id":"2202.10062","repositories_listed":1,"syntology":null},{"url":"/paper/parallel-sentence-mining-by-constrained","title":"Parallel Sentence Mining by Constrained Decoding","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-unsupervised-sentence","title":"MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases","date":"2020-05-01","arxiv_id":"2005.00352","repositories_listed":1,"syntology":null},{"url":"/paper/coursera-corpus-mining-and-multistage-fine","title":"Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation","date":"2019-12-26","arxiv_id":"1912.11739","repositories_listed":1,"syntology":null}],"syntology_records":1,"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"}}