{"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/multilingual-offensive-language","title":"Multilingual Offensive Language Identification with Cross-lingual Embeddings","arxiv_id":"2010.05324","date":"2020-10-11","proceeding":"EMNLP 2020 11","authors":["Tharindu Ranasinghe","Marcos Zampieri"],"abstract":"Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the various forms of such content (e.g. hate speech, cyberbulling, and cyberaggression). The clear majority of these studies deal with English partially because most annotated datasets available contain English data. In this paper, we take advantage of English data available by applying cross-lingual contextual word embeddings and transfer learning to make predictions in languages with less resources. We project predictions on comparable data in Bengali, Hindi, and Spanish and we report results of 0.8415 F1 macro for Bengali, 0.8568 F1 macro for Hindi, and 0.7513 F1 macro for Spanish. Finally, we show that our approach compares favorably to the best systems submitted to recent shared tasks on these three languages, confirming the robustness of cross-lingual contextual embeddings and transfer learning for this task.","url_abs":"https://arxiv.org/abs/2010.05324v1","url_pdf":"https://arxiv.org/pdf/2010.05324v1.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":"multilingual-offensive-language","repo_url":"https://github.com/tharindudr/DeepOffense","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-identification","task_name":"Language Identification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.05324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05324"}},"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":"deterministic:regex_extraction","url":"https://github.com/tharindudr/DeepOffense","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"d34c8ab039bdf946","entry":"encode","repo":"tharindudr/DeepOffense","repo_kind":"official","path":"deepoffense/language_modeling/language_modeling_utils.py","file_url":"https://github.com/tharindudr/DeepOffense/blob/HEAD/deepoffense/language_modeling/language_modeling_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d34c8ab039bdf946"}},{"code_sha256_prefix":"1369dca3f5bbc52a","entry":"encode_sliding_window","repo":"tharindudr/DeepOffense","repo_kind":"official","path":"deepoffense/language_modeling/language_modeling_utils.py","file_url":"https://github.com/tharindudr/DeepOffense/blob/HEAD/deepoffense/language_modeling/language_modeling_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1369dca3f5bbc52a"}},{"code_sha256_prefix":"37e86e14623d0254","entry":"mask_tokens","repo":"tharindudr/DeepOffense","repo_kind":"official","path":"deepoffense/language_modeling/language_modeling_utils.py","file_url":"https://github.com/tharindudr/DeepOffense/blob/HEAD/deepoffense/language_modeling/language_modeling_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37e86e14623d0254"}},{"code_sha256_prefix":"845d1017a8c6aacc","entry":"preprocess_batch_for_hf_dataset","repo":"tharindudr/DeepOffense","repo_kind":"official","path":"deepoffense/classification/classification_utils.py","file_url":"https://github.com/tharindudr/DeepOffense/blob/HEAD/deepoffense/classification/classification_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"845d1017a8c6aacc"}},{"code_sha256_prefix":"c38f7ab41a3dd3f0","entry":"preprocess_data_multiprocessing","repo":"tharindudr/DeepOffense","repo_kind":"official","path":"deepoffense/classification/classification_utils.py","file_url":"https://github.com/tharindudr/DeepOffense/blob/HEAD/deepoffense/classification/classification_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c38f7ab41a3dd3f0"}},{"code_sha256_prefix":"ed7096c541cce33f","entry":"sweep_config_to_sweep_values","repo":"tharindudr/DeepOffense","repo_kind":"official","path":"deepoffense/classification/classification_utils.py","file_url":"https://github.com/tharindudr/DeepOffense/blob/HEAD/deepoffense/classification/classification_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed7096c541cce33f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}