{"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/bridging-linguistic-typology-and-multilingual","title":"Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations","arxiv_id":"2004.14923","date":"2020-04-30","proceeding":"EMNLP 2020 11","authors":["Arturo Oncevay","Barry Haddow","Alexandra Birch"],"abstract":"Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language characterisation. We propose to fuse both views using singular vector canonical correlation analysis and study what kind of information is induced from each source. By inferring typological features and language phylogenies, we observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy in tasks that require information about language similarities, such as language clustering and ranking candidates for multilingual transfer. With our method, which is also released as a tool, we can easily project and assess new languages without expensive retraining of massive multilingual or ranking models, which are major disadvantages of related approaches.","url_abs":"https://arxiv.org/abs/2004.14923v2","url_pdf":"https://arxiv.org/pdf/2004.14923v2.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":"bridging-linguistic-typology-and-multilingual","repo_url":"https://github.com/aoncevay/multiview-langrep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.14923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14923"}},"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/aoncevay/multiview-langrep","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"35d992b5a786d6c3","entry":"compose_feats_matrix","repo":"aoncevay/multiview-langrep","repo_kind":"official","path":"src/compose_matrix.py","file_url":"https://github.com/aoncevay/multiview-langrep/blob/HEAD/src/compose_matrix.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":"35d992b5a786d6c3"}},{"code_sha256_prefix":"aea10d9dbc1f11ab","entry":"generate_list","repo":"aoncevay/multiview-langrep","repo_kind":"official","path":"clustering_analysis.py","file_url":"https://github.com/aoncevay/multiview-langrep/blob/HEAD/clustering_analysis.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":"aea10d9dbc1f11ab"}},{"code_sha256_prefix":"02e371816992267d","entry":"inertia_score","repo":"aoncevay/multiview-langrep","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/aoncevay/multiview-langrep/blob/HEAD/src/utils.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":"02e371816992267d"}},{"code_sha256_prefix":"36b1c1d2f1220a50","entry":"linkage_matrix","repo":"aoncevay/multiview-langrep","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/aoncevay/multiview-langrep/blob/HEAD/src/utils.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":"36b1c1d2f1220a50"}},{"code_sha256_prefix":"543dd32919b6af87","entry":"multiview_langrep","repo":"aoncevay/multiview-langrep","repo_kind":"official","path":"multiview_langrep.py","file_url":"https://github.com/aoncevay/multiview-langrep/blob/HEAD/multiview_langrep.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":"543dd32919b6af87"}},{"code_sha256_prefix":"02f8621ce672ab5b","entry":"svd_transform","repo":"aoncevay/multiview-langrep","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/aoncevay/multiview-langrep/blob/HEAD/src/utils.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":"02f8621ce672ab5b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}