Mausam, Das, Dinesh Raghu, Jyoti Rocktim, Vishal Saley, Goonjan Saha
We lifted 15 functions out of this paper's own repositories and ran 14 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| dair-iitd/MediTOD | canonical | 14 of 15 |
| Function | Status | Where it lives |
|---|---|---|
| bspan_to_constraint_dict | Ran | dair-iitd/MediTOD/src/llms/trainers.py pointer only (licence: NONE) · get_code("396d03485cea2e49") |
| formatting_prompts_func | Ran | dair-iitd/MediTOD/src/llama/infer.py pointer only (licence: NONE) · get_code("7c2702021405a385") |
| get_config | Ran | dair-iitd/MediTOD/src/llama/utils.py pointer only (licence: NONE) · get_code("3adae79ff63c5e7b") |
| get_joint_config | Ran | dair-iitd/MediTOD/src/llama/utils.py pointer only (licence: NONE) · get_code("02e79c020f752f87") |
| get_key_value_pairs_old | Ran | dair-iitd/MediTOD/metrics/pol_metrics.py pointer only (licence: NONE) · get_code("1bbbadc2316e66d1") |
| get_nlu_key_value_pairs | Ran | dair-iitd/MediTOD/src/llms/trainers.py pointer only (licence: NONE) · get_code("1cfaef942d92586b") |
| get_openai_results | Ran | dair-iitd/MediTOD/metrics/utils.py pointer only (licence: NONE) · get_code("588a5f552a18b6b8") |
| load_json | Ran | dair-iitd/MediTOD/metrics/nlg_metrics.py pointer only (licence: NONE) · get_code("6a08e1753f8b367c") |
| mean_pooling | Ran | dair-iitd/MediTOD/metrics/utils.py pointer only (licence: NONE) · get_code("77f69af078e09830") |
| override_config | Ran | dair-iitd/MediTOD/src/llama/utils.py pointer only (licence: NONE) · get_code("18fe9843588e7399") |
| parse_pptod_string | Ran | dair-iitd/MediTOD/metrics/pol_metrics.py pointer only (licence: NONE) · get_code("52abe40aafcc7692") |
| post_process | Ran | dair-iitd/MediTOD/src/llama/post.py pointer only (licence: NONE) · get_code("907ca7f3d23f9599") |
| post_punc | Ran | dair-iitd/MediTOD/src/llms/trainers.py pointer only (licence: NONE) · get_code("afbf31bdb3dab780") |
| preprocess_text | Ran | dair-iitd/MediTOD/metrics/nlg_metrics.py pointer only (licence: NONE) · get_code("a6ac4d0ef910ae31") |
| moses_multi_bleu | Not yet run | dair-iitd/MediTOD/metrics/nlg_metrics.py pointer only (licence: NONE) · get_code("e3ceca4e07925fcb") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 questionnairebased 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 release MediTOD resources for future research.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.14204")
get_code_for_paper("2410.14204")
have("2410.14204")
Connect an agent — have() is free.