{"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/unsupervised-multilingual-alignment-using","title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","arxiv_id":"2002.00743","date":"2020-01-28","proceeding":null,"authors":["Xin Lian","Kshitij Jain","Jakub Truszkowski","Pascal Poupart","Yao-Liang Yu"],"abstract":"We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the much simplified bilingual setting, by picking one of the input languages as the pivot language that we transit through. However, it is well-known that transiting through a poorly chosen pivot language (such as English) may severely degrade the translation quality, since the assumed transitive relations among all pairs of languages may not be enforced in the training process. Instead of going through a rather arbitrarily chosen pivot language, we propose to use the Wasserstein barycenter as a more informative \"mean\" language: it encapsulates information from all languages and minimizes all pairwise transportation costs. We evaluate our method on standard benchmarks and demonstrate state-of-the-art performances.","url_abs":"https://arxiv.org/abs/2002.00743v2","url_pdf":"https://arxiv.org/pdf/2002.00743v2.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-multilingual-alignment-using","repo_url":"https://github.com/alixxxin/multi-lang","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-machine-translation","task_name":"Unsupervised Machine Translation"},{"task_slug":"word-alignment","task_name":"Word Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/word-alignment-on-muse-en-de","task":"Word Alignment","dataset":"MUSE en-de","model":"Barycenter Alignment","rank_in_archive_order":1,"of":1,"metrics":{"P@1":"74.08"},"uses_additional_data":false},{"leaderboard":"/sota/word-alignment-on-muse-en-pt","task":"Word Alignment","dataset":"MUSE en-pt","model":"Barycenter Alignment","rank_in_archive_order":1,"of":1,"metrics":{"P@1":"84.65"},"uses_additional_data":false},{"leaderboard":"/sota/word-alignment-on-en-es","task":"Word Alignment","dataset":"en-es","model":"Barycenter Alignment","rank_in_archive_order":1,"of":2,"metrics":{"P@1":"84.26"},"uses_additional_data":false},{"leaderboard":"/sota/word-alignment-on-en-fr","task":"Word Alignment","dataset":"en-fr","model":"Barycenter Alignment","rank_in_archive_order":1,"of":2,"metrics":{"P@1":"82.94"},"uses_additional_data":false},{"leaderboard":"/sota/word-alignment-on-en-it","task":"Word Alignment","dataset":"en-it","model":"Barycenter Alignment","rank_in_archive_order":1,"of":1,"metrics":{"P@1":"81.45"},"uses_additional_data":false},{"leaderboard":"/sota/word-alignment-on-es-en","task":"Word Alignment","dataset":"es-en","model":"Barycenter Alignment","rank_in_archive_order":1,"of":2,"metrics":{"P@1":"83.5"},"uses_additional_data":false},{"leaderboard":"/sota/word-alignment-on-fr-en","task":"Word Alignment","dataset":"fr-en","model":"Barycenter Alignment","rank_in_archive_order":1,"of":2,"metrics":{"P@1":"83.23"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.00743","atlas_url":"https://app.syntology.ai/?focus=2002.00743","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2002.00743"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2002.00743\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2002.00743"},"call":"get_concepts_for_paper(arxiv_id=\"2002.00743\")"}],"by_repo":[{"repo":"alixxxin/multi-lang","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"8aa22003db917339109f211c5403a2e834f56fcbbe56fd2a5df4b98d9db4b727","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}