{"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/exploiting-sentence-order-in-document","title":"Exploiting Sentence Order in Document Alignment","arxiv_id":"2004.14523","date":"2020-04-30","proceeding":"EMNLP 2020 11","authors":["Brian Thompson","Philipp Koehn"],"abstract":"We present a simple document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring. Our method results in 61% relative reduction in error compared to the best previously published result on the WMT16 document alignment shared task. Our method improves downstream MT performance on web-scraped Sinhala--English documents from ParaCrawl, outperforming the document alignment method used in the most recent ParaCrawl release. It also outperforms a comparable corpora method which uses the same multilingual embeddings, demonstrating that exploiting sentence order is beneficial even if the end goal is sentence-level bitext.","url_abs":"https://arxiv.org/abs/2004.14523v2","url_pdf":"https://arxiv.org/pdf/2004.14523v2.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":"exploiting-sentence-order-in-document","repo_url":"https://github.com/thompsonb/vecalign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.14523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14523"}},"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/facebookresearch/LASER","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thompsonb/vecalign","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_fixture":1,"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"ce7491b4961154f3","entry":"score","repo":"facebookresearch/LASER","repo_kind":"found_in_text","path":"source/mine_bitexts.py","file_url":"https://github.com/facebookresearch/LASER/blob/HEAD/source/mine_bitexts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ce7491b4961154f3"}},{"code_sha256_prefix":"d89e697e2a60269c","entry":"score_candidates","repo":"facebookresearch/LASER","repo_kind":"found_in_text","path":"source/mine_bitexts.py","file_url":"https://github.com/facebookresearch/LASER/blob/HEAD/source/mine_bitexts.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d89e697e2a60269c"}},{"code_sha256_prefix":"8a937937aede187b","entry":"build_doc_embedding","repo":"thompsonb/vecalign","repo_kind":"official","path":"vecalign/standalone_document_embedding_demo.py","file_url":"https://github.com/thompsonb/vecalign/blob/HEAD/vecalign/standalone_document_embedding_demo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a937937aede187b"}},{"code_sha256_prefix":"8480418ca87edb70","entry":"make_doc_embedding","repo":"thompsonb/vecalign","repo_kind":"official","path":"vecalign/dp_utils.py","file_url":"https://github.com/thompsonb/vecalign/blob/HEAD/vecalign/dp_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8480418ca87edb70"}},{"code_sha256_prefix":"546f4fc8cee2587b","entry":"pert_pdf_normalized","repo":"thompsonb/vecalign","repo_kind":"official","path":"vecalign/standalone_document_embedding_demo.py","file_url":"https://github.com/thompsonb/vecalign/blob/HEAD/vecalign/standalone_document_embedding_demo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"546f4fc8cee2587b"}},{"code_sha256_prefix":"eb8f2845c132102e","entry":"preprocess_line","repo":"thompsonb/vecalign","repo_kind":"official","path":"vecalign/dp_utils.py","file_url":"https://github.com/thompsonb/vecalign/blob/HEAD/vecalign/dp_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb8f2845c132102e"}},{"code_sha256_prefix":"83237f782dedf200","entry":"read_in_embeddings","repo":"thompsonb/vecalign","repo_kind":"official","path":"vecalign/dp_utils.py","file_url":"https://github.com/thompsonb/vecalign/blob/HEAD/vecalign/dp_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83237f782dedf200"}},{"code_sha256_prefix":"2655212d4b431740","entry":"score_multiple","repo":"thompsonb/vecalign","repo_kind":"official","path":"vecalign/score.py","file_url":"https://github.com/thompsonb/vecalign/blob/HEAD/vecalign/score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2655212d4b431740"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}