{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/improving-word-translation-via-two-stage","title":"Improving Word Translation via Two-Stage Contrastive Learning","arxiv_id":null,"date":"2021-11-16","proceeding":"ACL ARR November 2021 11","authors":["Anonymous"],"abstract":"Word translation or bilingual lexicon induction (BLI) is a key cross-lingual task, aiming to bridge the lexical gap between different languages. In this work, we propose a robust and effective two-stage contrastive learning framework for the BLI task. As Stage C1, we propose to refine standard cross-lingual linear maps between static word embeddings (WEs) via a contrastive learning objective; we also show how to integrate it into the self-learning procedure for even more refined cross-lingual maps. In Stage C2, we conduct BLI-oriented contrastive fine-tuning of mBERT, unlocking its word translation capability. We also show that static WEs induced from the 'C2-tuned' mBERT complement static WEs from Stage C1. Comprehensive experiments on standard BLI datasets for diverse languages and different experimental setups demonstrate substantial gains achieved by our framework. While the BLI method from Stage C1 already yields substantial gains over all state-of-the-art BLI methods in our comparison, even stronger improvements are met with the full two-stage framework: e.g., we report gains for 112/112 BLI setups, spanning 28 language pairs.\n","url_abs":"https://openreview.net/forum?id=ycgOlOnbbMq","url_pdf":"https://openreview.net/pdf?id=ycgOlOnbbMq","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":"improving-word-translation-via-two-stage","repo_url":"https://github.com/cambridgeltl/contrastivebli","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bilingual-lexicon-induction","task_name":"Bilingual Lexicon Induction"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"cross-lingual-word-embeddings","task_name":"Cross-Lingual Word Embeddings"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multilingual-nlp","task_name":"Multilingual NLP"},{"task_slug":"multilingual-word-embeddings","task_name":"Multilingual Word Embeddings"},{"task_slug":"pretrained-multilingual-language-models","task_name":"Pretrained Multilingual Language Models"},{"task_slug":"self-learning","task_name":"Self-Learning"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"},{"task_slug":"word-alignment","task_name":"Word Alignment"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-translation","task_name":"Word Translation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"gradual-self-training","method_name":"Gradual Self-Training"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"procrustes","method_name":"Procrustes"},{"method_slug":"self-learning","method_name":"Self-Learning"},{"method_slug":"fasttext","method_name":"fastText"},{"method_slug":"mbert","method_name":"mBERT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"cambridgeltl/contrastivebli","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2203.08307"],"harvested_for_calls":[{"arxiv_id":"2203.08307","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.08307"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.08307\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7f990a5e329afd5f78e30dd4c4deafc9a2ba8c808e3f89fcc1bfd994ae76818a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}