{"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/simalign-high-quality-word-alignments-without","title":"SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings","arxiv_id":"2004.08728","date":"2020-04-18","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Masoud Jalili Sabet","Philipp Dufter","François Yvon","Hinrich Schütze"],"abstract":"Word alignments are useful for tasks like statistical and neural machine translation (NMT) and cross-lingual annotation projection. Statistical word aligners perform well, as do methods that extract alignments jointly with translations in NMT. However, most approaches require parallel training data, and quality decreases as less training data is available. We propose word alignment methods that require no parallel data. The key idea is to leverage multilingual word embeddings, both static and contextualized, for word alignment. Our multilingual embeddings are created from monolingual data only without relying on any parallel data or dictionaries. We find that alignments created from embeddings are superior for four and comparable for two language pairs compared to those produced by traditional statistical aligners, even with abundant parallel data; e.g., contextualized embeddings achieve a word alignment F1 for English-German that is 5 percentage points higher than eflomal, a high-quality statistical aligner, trained on 100k parallel sentences.","url_abs":"https://arxiv.org/abs/2004.08728v4","url_pdf":"https://arxiv.org/pdf/2004.08728v4.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":"simalign-high-quality-word-alignments-without","repo_url":"https://github.com/masoudjs/simalign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simalign-high-quality-word-alignments-without","repo_url":"https://github.com/cisnlp/simalign","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simalign-high-quality-word-alignments-without","repo_url":"https://github.com/ikergarcia1996/easy-label-projection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multilingual-word-embeddings","task_name":"Multilingual Word Embeddings"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-alignment","task_name":"Word Alignment"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.08728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08728"}},"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/cisnlp/simalign","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/robertostling/eflomal","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"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":"9be91b30408c62ce","entry":"get_logger","repo":"cisnlp/simalign","repo_kind":"listed","path":"simalign/simalign.py","file_url":"https://github.com/cisnlp/simalign/blob/HEAD/simalign/simalign.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9be91b30408c62ce"}},{"code_sha256_prefix":"bc2f97ee585972e6","entry":"EmbeddingLoader","repo":"cisnlp/simalign","repo_kind":"listed","path":"simalign/simalign.py","file_url":"https://github.com/cisnlp/simalign/blob/HEAD/simalign/simalign.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc2f97ee585972e6"}},{"code_sha256_prefix":"a6dd016f10ca4d0f","entry":"SentenceAligner","repo":"cisnlp/simalign","repo_kind":"listed","path":"simalign/simalign.py","file_url":"https://github.com/cisnlp/simalign/blob/HEAD/simalign/simalign.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6dd016f10ca4d0f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}