{"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/parallel-sentence-mining-by-constrained","title":"Parallel Sentence Mining by Constrained Decoding","arxiv_id":null,"date":"2020-07-01","proceeding":"ACL 2020 6","authors":["Pin-zhen Chen","Nikolay Bogoychev","Kenneth Heafield","Faheem Kirefu"],"abstract":"We present a novel method to extract parallel sentences from two monolingual corpora, using neural machine translation. Our method relies on translating sentences in one corpus, but constraining the decoding by a prefix tree built on the other corpus. We argue that a neural machine translation system by itself can be a sentence similarity scorer and it efficiently approximates pairwise comparison with a modified beam search. When benchmarked on the BUCC shared task, our method achieves results comparable to other submissions.","url_abs":"https://aclanthology.org/2020.acl-main.152","url_pdf":"https://aclanthology.org/2020.acl-main.152.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":"parallel-sentence-mining-by-constrained","repo_url":"https://github.com/marian-nmt/marian-dev","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"cross-lingual-bitext-mining","task_name":"Cross-Lingual Bitext Mining"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"parallel-corpus-mining","task_name":"Parallel Corpus Mining"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-similarity","task_name":"Sentence Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}