{"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/meditod-an-english-dialogue-dataset-for","title":"MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations","arxiv_id":"2410.14204","date":"2024-10-18","proceeding":null,"authors":["Vishal Vivek Saley","Goonjan Saha","Rocktim Jyoti Das","Dinesh Raghu","Mausam"],"abstract":"Medical task-oriented dialogue systems can assist doctors by collecting patient medical history, aiding in diagnosis, or guiding treatment selection, thereby reducing doctor burnout and expanding access to medical services. However, doctor-patient dialogue datasets are not readily available, primarily due to privacy regulations. Moreover, existing datasets lack comprehensive annotations involving medical slots and their different attributes, such as symptoms and their onset, progression, and severity. These comprehensive annotations are crucial for accurate diagnosis. Finally, most existing datasets are non-English, limiting their utility for the larger research community. In response, we introduce MediTOD, a new dataset of doctor-patient dialogues in English for the medical history-taking task. Collaborating with doctors, we devise a questionnaire-based labeling scheme tailored to the medical domain. Then, medical professionals create the dataset with high-quality comprehensive annotations, capturing medical slots and their attributes. We establish benchmarks in supervised and few-shot settings on MediTOD for natural language understanding, policy learning, and natural language generation subtasks, evaluating models from both TOD and biomedical domains. We make MediTOD publicly available for future research.","url_abs":"https://arxiv.org/abs/2410.14204v1","url_pdf":"https://arxiv.org/pdf/2410.14204v1.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":[],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.14204","atlas_url":"https://app.syntology.ai/?focus=2410.14204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14204"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/dair-iitd/MediTOD","reach":{"status":"ok"}}],"summary":{"ran":13,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":15,"ran":14,"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":15,"samples":[{"code_sha256_prefix":"396d03485cea2e49","entry":"bspan_to_constraint_dict","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llms/trainers.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llms/trainers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"396d03485cea2e49"}},{"code_sha256_prefix":"7c2702021405a385","entry":"formatting_prompts_func","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llama/infer.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llama/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7c2702021405a385"}},{"code_sha256_prefix":"3adae79ff63c5e7b","entry":"get_config","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llama/utils.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llama/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3adae79ff63c5e7b"}},{"code_sha256_prefix":"02e79c020f752f87","entry":"get_joint_config","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llama/utils.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llama/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02e79c020f752f87"}},{"code_sha256_prefix":"1bbbadc2316e66d1","entry":"get_key_value_pairs_old","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"metrics/pol_metrics.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/metrics/pol_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1bbbadc2316e66d1"}},{"code_sha256_prefix":"1cfaef942d92586b","entry":"get_nlu_key_value_pairs","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llms/trainers.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llms/trainers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1cfaef942d92586b"}},{"code_sha256_prefix":"588a5f552a18b6b8","entry":"get_openai_results","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"metrics/utils.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/metrics/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"588a5f552a18b6b8"}},{"code_sha256_prefix":"6a08e1753f8b367c","entry":"load_json","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"metrics/nlg_metrics.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/metrics/nlg_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a08e1753f8b367c"}},{"code_sha256_prefix":"77f69af078e09830","entry":"mean_pooling","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"metrics/utils.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/metrics/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77f69af078e09830"}},{"code_sha256_prefix":"18fe9843588e7399","entry":"override_config","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llama/utils.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llama/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"18fe9843588e7399"}},{"code_sha256_prefix":"52abe40aafcc7692","entry":"parse_pptod_string","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"metrics/pol_metrics.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/metrics/pol_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52abe40aafcc7692"}},{"code_sha256_prefix":"907ca7f3d23f9599","entry":"post_process","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llama/post.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llama/post.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"907ca7f3d23f9599"}},{"code_sha256_prefix":"afbf31bdb3dab780","entry":"post_punc","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"src/llms/trainers.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llms/trainers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"afbf31bdb3dab780"}},{"code_sha256_prefix":"a6ac4d0ef910ae31","entry":"preprocess_text","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"metrics/nlg_metrics.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/metrics/nlg_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6ac4d0ef910ae31"}},{"code_sha256_prefix":"e3ceca4e07925fcb","entry":"moses_multi_bleu","repo":"dair-iitd/MediTOD","repo_kind":"found_in_text","path":"metrics/nlg_metrics.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/metrics/nlg_metrics.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":"e3ceca4e07925fcb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}