{"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/bitod-a-bilingual-multi-domain-dataset-for","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","arxiv_id":"2106.02787","date":"2021-06-05","proceeding":null,"authors":["Zhaojiang Lin","Andrea Madotto","Genta Indra Winata","Peng Xu","Feijun Jiang","Yuxiang Hu","Chen Shi","Pascale Fung"],"abstract":"Task-oriented dialogue (ToD) benchmarks provide an important avenue to measure progress and develop better conversational agents. However, existing datasets for end-to-end ToD modeling are limited to a single language, hindering the development of robust end-to-end ToD systems for multilingual countries and regions. Here we introduce BiToD, the first bilingual multi-domain dataset for end-to-end task-oriented dialogue modeling. BiToD contains over 7k multi-domain dialogues (144k utterances) with a large and realistic bilingual knowledge base. It serves as an effective benchmark for evaluating bilingual ToD systems and cross-lingual transfer learning approaches. We provide state-of-the-art baselines under three evaluation settings (monolingual, bilingual, and cross-lingual). The analysis of our baselines in different settings highlights 1) the effectiveness of training a bilingual ToD system compared to two independent monolingual ToD systems, and 2) the potential of leveraging a bilingual knowledge base and cross-lingual transfer learning to improve the system performance under low resource condition.","url_abs":"https://arxiv.org/abs/2106.02787v1","url_pdf":"https://arxiv.org/pdf/2106.02787v1.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":"bitod-a-bilingual-multi-domain-dataset-for","repo_url":"https://github.com/HLTCHKUST/BiToD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"bitod","name":"BiToD","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.02787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02787"}},"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/HLTCHKUST/BiToD","reach":null}],"summary":{"ran_draft_wrong":4,"ran_violates":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"16527c949b0dad20","entry":"compute_lev_span","repo":"HLTCHKUST/BiToD","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/HLTCHKUST/BiToD/blob/HEAD/preprocess.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"16527c949b0dad20"}},{"code_sha256_prefix":"c6ce652bfb099994","entry":"is_int","repo":"HLTCHKUST/BiToD","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/HLTCHKUST/BiToD/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6ce652bfb099994"}},{"code_sha256_prefix":"263abb1c666a9c10","entry":"knowledge2span","repo":"HLTCHKUST/BiToD","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/HLTCHKUST/BiToD/blob/HEAD/preprocess.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"263abb1c666a9c10"}},{"code_sha256_prefix":"fe6b1382a7dc0e63","entry":"span2dict","repo":"HLTCHKUST/BiToD","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/HLTCHKUST/BiToD/blob/HEAD/evaluate.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe6b1382a7dc0e63"}},{"code_sha256_prefix":"99cd7c02bcd44503","entry":"state2span","repo":"HLTCHKUST/BiToD","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/HLTCHKUST/BiToD/blob/HEAD/preprocess.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"99cd7c02bcd44503"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}