{"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/metaxl-meta-representation-transformation-for","title":"MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning","arxiv_id":"2104.07908","date":"2021-04-16","proceeding":"NAACL 2021 4","authors":["Mengzhou Xia","Guoqing Zheng","Subhabrata Mukherjee","Milad Shokouhi","Graham Neubig","Ahmed Hassan Awadallah"],"abstract":"The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without large-scale monolingual corpora for pre-training or sufficient annotated data for fine-tuning, transfer learning remains an under-studied and challenging task. Moreover, recent work shows that multilingual representations are surprisingly disjoint across languages, bringing additional challenges for transfer onto extremely low-resource languages. In this paper, we propose MetaXL, a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer. Extensive experiments on real-world low-resource languages - without access to large-scale monolingual corpora or large amounts of labeled data - for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach. Code for MetaXL is publicly available at github.com/microsoft/MetaXL.","url_abs":"https://arxiv.org/abs/2104.07908v1","url_pdf":"https://arxiv.org/pdf/2104.07908v1.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":"metaxl-meta-representation-transformation-for","repo_url":"https://github.com/microsoft/MetaXL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"metaxl-meta-representation-transformation-for","repo_url":"https://github.com/liatb282/metaxlr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.07908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07908"}},"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/liatb282/metaxlr","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/microsoft/MetaXL","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1},"listed":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"691a05c33aab632f","entry":"_dot","repo":"microsoft/MetaXL","repo_kind":"official","path":"mlt.py","file_url":"https://github.com/microsoft/MetaXL/blob/HEAD/mlt.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"691a05c33aab632f"}},{"code_sha256_prefix":"3c561bc9240f884c","entry":"masked_cross_entropy","repo":"microsoft/MetaXL","repo_kind":"official","path":"mlt.py","file_url":"https://github.com/microsoft/MetaXL/blob/HEAD/mlt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c561bc9240f884c"}},{"code_sha256_prefix":"22ba58ab2e67adae","entry":"masked_cross_entropy_longvector","repo":"microsoft/MetaXL","repo_kind":"official","path":"mlt.py","file_url":"https://github.com/microsoft/MetaXL/blob/HEAD/mlt.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22ba58ab2e67adae"}},{"code_sha256_prefix":"3ced20a5adc3c80e","entry":"step_metaxl","repo":"microsoft/MetaXL","repo_kind":"official","path":"mlt.py","file_url":"https://github.com/microsoft/MetaXL/blob/HEAD/mlt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ced20a5adc3c80e"}},{"code_sha256_prefix":"624d7acf663ae752","entry":"calculate_parameters","repo":"liatb282/metaxlr","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"624d7acf663ae752"}},{"code_sha256_prefix":"c76c28eb3d0f2d48","entry":"distr","repo":"liatb282/metaxlr","repo_kind":"listed","path":"mtrain.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/mtrain.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c76c28eb3d0f2d48"}},{"code_sha256_prefix":"ea581ea3f25dd281","entry":"draw","repo":"liatb282/metaxlr","repo_kind":"listed","path":"mtrain.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/mtrain.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"ea581ea3f25dd281"}},{"code_sha256_prefix":"b00098ec748c4d57","entry":"find_index","repo":"liatb282/metaxlr","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b00098ec748c4d57"}},{"code_sha256_prefix":"9ba80da0d76244fa","entry":"masked_cross_entropy","repo":"liatb282/metaxlr","repo_kind":"listed","path":"models.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9ba80da0d76244fa"}},{"code_sha256_prefix":"ec26c809cf2ea367","entry":"permute_aug","repo":"liatb282/metaxlr","repo_kind":"listed","path":"mlt.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/mlt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"ec26c809cf2ea367"}},{"code_sha256_prefix":"804969f23b1b82b8","entry":"sync_autograd","repo":"liatb282/metaxlr","repo_kind":"listed","path":"mlt.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/mlt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"804969f23b1b82b8"}},{"code_sha256_prefix":"72f0841ee3deb1f5","entry":"sync_backward","repo":"microsoft/MetaXL","repo_kind":"official","path":"mlt.py","file_url":"https://github.com/microsoft/MetaXL/blob/HEAD/mlt.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":"72f0841ee3deb1f5"}},{"code_sha256_prefix":"30328e1cfdcf3c85","entry":"trim_input","repo":"liatb282/metaxlr","repo_kind":"listed","path":"models.py","file_url":"https://github.com/liatb282/metaxlr/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"30328e1cfdcf3c85"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}