{"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/unsupervised-cross-lingual-transfer-of-word","title":"Unsupervised Cross-lingual Transfer of Word Embedding Spaces","arxiv_id":"1809.03633","date":"2018-09-10","proceeding":"EMNLP 2018 10","authors":["Ruochen Xu","Yiming Yang","Naoki Otani","Yuexin Wu"],"abstract":"Cross-lingual transfer of word embeddings aims to establish the semantic\nmappings among words in different languages by learning the transformation\nfunctions over the corresponding word embedding spaces. Successfully solving\nthis problem would benefit many downstream tasks such as to translate text\nclassification models from resource-rich languages (e.g. English) to\nlow-resource languages. Supervised methods for this problem rely on the\navailability of cross-lingual supervision, either using parallel corpora or\nbilingual lexicons as the labeled data for training, which may not be available\nfor many low resource languages. This paper proposes an unsupervised learning\napproach that does not require any cross-lingual labeled data. Given two\nmonolingual word embedding spaces for any language pair, our algorithm\noptimizes the transformation functions in both directions simultaneously based\non distributional matching as well as minimizing the back-translation losses.\nWe use a neural network implementation to calculate the Sinkhorn distance, a\nwell-defined distributional similarity measure, and optimize our objective\nthrough back-propagation. Our evaluation on benchmark datasets for bilingual\nlexicon induction and cross-lingual word similarity prediction shows stronger\nor competitive performance of the proposed method compared to other\nstate-of-the-art supervised and unsupervised baseline methods over many\nlanguage pairs.","url_abs":"http://arxiv.org/abs/1809.03633v1","url_pdf":"http://arxiv.org/pdf/1809.03633v1.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":"unsupervised-cross-lingual-transfer-of-word","repo_url":"https://github.com/xrc10/unsup-cross-lingual-embedding-transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"bilingual-lexicon-induction","task_name":"Bilingual Lexicon Induction"},{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-similarity","task_name":"Word Similarity"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.03633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.03633"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xrc10/unsup-cross-lingual-embedding-transfer","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"a00df19c529a2278","entry":"get_logger","repo":"xrc10/unsup-cross-lingual-embedding-transfer","repo_kind":"official","path":"src/runner.py","file_url":"https://github.com/xrc10/unsup-cross-lingual-embedding-transfer/blob/HEAD/src/runner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a00df19c529a2278"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}