{"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/sentalign-accurate-and-scalable-sentence","title":"SentAlign: Accurate and Scalable Sentence Alignment","arxiv_id":"2311.08982","date":"2023-11-15","proceeding":null,"authors":["Steinþór Steingrímsson","Hrafn Loftsson","Andy Way"],"abstract":"We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs. Given user-defined parameters, the alignment algorithm evaluates all possible alignment paths in fairly large documents of thousands of sentences and uses a divide-and-conquer approach to align documents containing tens of thousands of sentences. The scoring function is based on LaBSE bilingual sentence representations. SentAlign outperforms five other sentence alignment tools when evaluated on two different evaluation sets, German-French and English-Icelandic, and on a downstream machine translation task.","url_abs":"https://arxiv.org/abs/2311.08982v1","url_pdf":"https://arxiv.org/pdf/2311.08982v1.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":"sentalign-accurate-and-scalable-sentence","repo_url":"https://github.com/steinst/sentalign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.08982","atlas_url":"https://app.syntology.ai/?focus=2311.08982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08982"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/steinst/sentalign","reach":null}],"summary":{"ran_draft_wrong":7,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":0,"samples":[{"code_sha256_prefix":"a96e7e2f0548f8b5","entry":"add_nulls","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a96e7e2f0548f8b5"}},{"code_sha256_prefix":"493838232d77d877","entry":"check_for_nulls","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"493838232d77d877"}},{"code_sha256_prefix":"bb9416f36b47caaf","entry":"concat_strings","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb9416f36b47caaf"}},{"code_sha256_prefix":"6b9787c8d7cf5c19","entry":"create_combinations_from_concatenations","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b9787c8d7cf5c19"}},{"code_sha256_prefix":"b674d206c22a46ac","entry":"create_concats","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b674d206c22a46ac"}},{"code_sha256_prefix":"fc921754526f6839","entry":"get_highest_scoring_pairs","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc921754526f6839"}},{"code_sha256_prefix":"3524d3d98293aa63","entry":"get_labse_score","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3524d3d98293aa63"}},{"code_sha256_prefix":"c7ebf2f9d86ba79d","entry":"reevaluate_path","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7ebf2f9d86ba79d"}},{"code_sha256_prefix":"5c4014d6f76d370c","entry":"align_anchors","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.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":"5c4014d6f76d370c"}},{"code_sha256_prefix":"8358c8ed0b6c07e5","entry":"fill_null_aligns","repo":"steinst/sentalign","repo_kind":"official","path":"align_anchors.py","file_url":"https://github.com/steinst/sentalign/blob/HEAD/align_anchors.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":"8358c8ed0b6c07e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}