{"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-the-domain-gap-in-cross-lingual","title":"Bridging the domain gap in cross-lingual document classification","arxiv_id":"1909.07009","date":"2019-09-16","proceeding":null,"authors":["Guokun Lai","Barlas Oguz","Yiming Yang","Veselin Stoyanov"],"abstract":"The scarcity of labeled training data often prohibits the internationalization of NLP models to multiple languages. Recent developments in cross-lingual understanding (XLU) has made progress in this area, trying to bridge the language barrier using language universal representations. However, even if the language problem was resolved, models trained in one language would not transfer to another language perfectly due to the natural domain drift across languages and cultures. We consider the setting of semi-supervised cross-lingual understanding, where labeled data is available in a source language (English), but only unlabeled data is available in the target language. We combine state-of-the-art cross-lingual methods with recently proposed methods for weakly supervised learning such as unsupervised pre-training and unsupervised data augmentation to simultaneously close both the language gap and the domain gap in XLU. We show that addressing the domain gap is crucial. We improve over strong baselines and achieve a new state-of-the-art for cross-lingual document classification.","url_abs":"https://arxiv.org/abs/1909.07009v2","url_pdf":"https://arxiv.org/pdf/1909.07009v2.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-the-domain-gap-in-cross-lingual","repo_url":"https://github.com/laiguokun/xlu-data","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"cross-domain-document-classification","task_name":"Cross-Domain Document Classification"},{"task_slug":"cross-lingual-document-classification","task_name":"Cross-Lingual Document Classification"},{"task_slug":"cross-lingual-sentiment-classification","task_name":"Cross-Lingual Sentiment Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-lingual-document-classification-on-8","task":"Cross-Lingual Document Classification","dataset":"MLDoc Zero-Shot English-to-Chinese","model":"XLMft UDA","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"93.32"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-document-classification-on-2","task":"Cross-Lingual Document Classification","dataset":"MLDoc Zero-Shot English-to-French","model":"XLMft UDA","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"96.05"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-document-classification-on","task":"Cross-Lingual Document Classification","dataset":"MLDoc Zero-Shot English-to-German","model":"XLMft UDA","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"96.95%"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-document-classification-on-9","task":"Cross-Lingual Document Classification","dataset":"MLDoc Zero-Shot English-to-Russian","model":"XLMft UDA","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-document-classification-on-1","task":"Cross-Lingual Document Classification","dataset":"MLDoc Zero-Shot English-to-Spanish","model":"XLMft UDA","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"96.8"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1909.07009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07009"}},"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/laiguokun/xlu-data","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"3dc2e92d3c81a4b7","entry":"processItem","repo":"laiguokun/xlu-data","repo_kind":"official","path":"cross-lingual-amazon/parse-acl10.py","file_url":"https://github.com/laiguokun/xlu-data/blob/HEAD/cross-lingual-amazon/parse-acl10.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":"3dc2e92d3c81a4b7"}},{"code_sha256_prefix":"d571bc0c8db12660","entry":"parse","repo":"laiguokun/xlu-data","repo_kind":"official","path":"cross-lingual-amazon/parse-acl10.py","file_url":"https://github.com/laiguokun/xlu-data/blob/HEAD/cross-lingual-amazon/parse-acl10.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d571bc0c8db12660"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}