{ "schema_version": "2.0", "record_type": "dataset", "tier": "verified", "slug": "meddg", "name": "MedDG", "summary": { "zh": "许可证声明：未声明（NOASSERTION）；本站处理：待确认，暂只链接原出处。许可证未声明许可：仓库 GPL-3.0，是否覆盖数据未说明；确认前只链接原出处。", "en": "License: unstated (NOASSERTION); Mdexa hosting: pending. License unstated: GPL-3.0 repository license; whether it covers the data is unstated; link only until resolved." }, "systems": [ "modern-medicine" ], "domains": [ "clinical-medicine" ], "content_types": [ "qa-dialogue", "annotated-corpus" ], "content_description": { "en": "Gastroenterology consultation dialogues (entity-annotated)", "zh": "消化科问诊对话（实体标注）" }, "languages": [ "zh" ], "modalities": [ "text" ], "size": { "raw": "17,864段对话、385,951条话语、217,205个实体（搜索摘要）", "measures": [ { "value": 17864, "unit": "dialogues", "qualifier": "claimed", "scope": "search snippet" }, { "value": 385951, "unit": "utterances", "qualifier": "claimed", "scope": "search snippet" }, { "value": 217205, "unit": "entities", "qualifier": "claimed", "scope": "search snippet" } ] }, "publisher": "lwgkzl（Liu 等，2020）", "year": { "value": 2020, "raw": "2020" }, "expert_review": { "en": "Entity annotation (paper); physician review not stated", "zh": "实体标注（论文）；未说明医生审核" }, "license": { "legacy_status": "pending", "spdx": "NOASSERTION", "commercial_use": "unstated", "derivatives": "unstated", "redistribution": "unstated", "rationale": { "en": "GPL-3.0 repository license; whether it covers the data is unstated", "zh": "仓库 GPL-3.0，是否覆盖数据未说明" }, "evidence": [ { "location": "repo-license", "location_detail": { "en": "GitHub repository license: GPL-3.0; page does not say whether it covers the data (data on Google Drive)", "zh": "GitHub 仓库许可证：GPL-3.0；页面未说明是否覆盖数据（数据托管于 Google Drive）" }, "excerpt": "GNU GENERAL PUBLIC LICENSE\nVersion 3, 29 June 2007", "spdx": "GPL-3.0", "url": "https://github.com/lwgkzl/MedDG", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "secondhand": false } ] }, "license_status": "unstated", "hosting": "pending", "hosting_reason": { "zh": "许可证未声明许可：仓库 GPL-3.0，是否覆盖数据未说明；确认前只链接原出处。", "en": "License unstated: GPL-3.0 repository license; whether it covers the data is unstated; link only until resolved." }, "signoff": null, "repo_license": { "spdx": "GPL-3.0", "source": "license-file", "verified": true, "snapshot_id": "s02", "url": "https://github.com/lwgkzl/MedDG" }, "risk_flags": [ "scraped", "real-patient-text" ], "provenance": { "source_description": { "en": "Gastroenterology section of an online medical consultation website (search snippet)", "zh": "在线医疗问诊网站消化科（搜索摘要）" }, "upstream": [] }, "known_issues": [ { "en": "Terms of the source website not checked", "zh": "数据来源网站条款未核" }, { "en": "Whether GPL-3.0 covers the data is not stated", "zh": "GPL-3.0 能否覆盖数据未说明" } ], "preflight": { "status": "not-run" }, "access": { "mdexa_download": null, "external_urls": [ "https://github.com/lwgkzl/MedDG" ], "notes": null }, "citation": { "text": null, "bibtex": null, "references": [] }, "verification_level": "partially-verified", "last_verified": "2026-11-12", "tags": [ { "facet": "task_format", "value": "multi-turn-dialogue", "basis": "author-stated", "excerpt": "[MedDG: an entity-centric medical consultation dataset for entity-aware medical dialogue generation](https://link.springer.com/chapter/10.1007/978-3-031-17120-8_35)", "snapshot_id": "s01" }, { "facet": "task_format", "value": "ner", "basis": "inferred", "inferred_from": "card-content-description", "note": { "en": "Entity annotation.", "zh": "实体标注" } }, { "facet": "condition_scope", "value": "icd11-13", "basis": "derived", "derived_from": { "facet": "specialty", "value": "gastroenterology" }, "note": { "zh": "由专科（消化内科）按对应表派生", "en": "Derived from specialty gastroenterology via mapping" } }, { "facet": "specialty", "value": "gastroenterology", "basis": "inferred", "inferred_from": "card-source", "note": { "zh": "卡片称来自问诊网站消化科（搜索摘要，低置信）", "en": "Gastroenterology section (snippet; low confidence)" } } ], "changelog": [ { "date": "2026-11-12", "change": { "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.", "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。" } }, { "date": "2026-11-12", "change": { "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.", "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。" } }, { "date": "2026-11-12", "change": { "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.", "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。" } }, { "date": "2026-11-12", "change": { "en": "Recorded the code repository license separately; it is not treated as a data license statement.", "zh": "单独记录代码仓库许可证，不视为数据许可声明。" } }, { "date": "2026-11-13", "change": { "en": "Added dataset-level tags: 4 (1 stated by the authors with excerpts, 3 inferred from the content). No conclusion changed.", "zh": "新增数据集标签 4 个（作者声明 1 个，附逐字摘录；据内容推断 3 个）；未改动任何结论。" } }, { "date": "2026-11-13", "change": { "en": "Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.", "zh": "移除存储的规模档位标签；档位改为生成页面时由 size 字段计算。" } }, { "date": "2026-11-13", "change": { "en": "Added specialty tags: gastroenterology(inferred).", "zh": "新增专科标签：gastroenterology(inferred)。" } } ], "access_recipe": { "verified_on": "2026-11-14", "platform": "github", "repo_id": "lwgkzl/MedDG", "source": { "api_url": "https://api.github.com/repos/lwgkzl/MedDG", "fetched_on": "2026-11-14" }, "access_state": "open", "files": [], "files_truncated": false, "commands": [ { "command": "git clone https://github.com/lwgkzl/MedDG", "evidence": { "excerpt": "git clone https://github.com/YOUR-USERNAME/YOUR-REPOSITORY", "doc": "github-clone", "url": "https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository", "fetched_on": "2026-11-14" } } ], "registration": null, "version": { "commit": null, "last_modified": "2023-03-19T11:44:48Z", "default_branch": "master" }, "license_note": { "license_status": "unstated", "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely." }, "gaps": [ "the platform publishes no checksum for these files; none was computed (we do not download data files)" ] }, "_links": { "text": "在本库继续查找。本条目是 109 条已处理并核实的记录之一（数据集、数据资源与开源模型）。查找其他条目：调用 `https://mcp.mdexa.com/v1/datasets?q=<关键词>`，或连接 MCP 服务 `https://mcp.mdexa.com/mcp`；每分钟 20 次以内无需密钥。每行返回不到 1 KB；空结果即\"数据库未收录\"。核对一份清单：一次批量核对（免费账号）即返回报告。说明：/agents.md。相似条目：IMCS-21 (https://mdexa.com/zh/datasets/imcs-21/)；CMtMedQA (https://mdexa.com/zh/datasets/cmtmedqa/)；DISC-Med-SFT (https://mdexa.com/zh/datasets/disc-med-sft/)。", "records": 109, "search": { "template": "https://mcp.mdexa.com/v1/datasets?q={words}", "example": "https://mcp.mdexa.com/v1/datasets?q=%E7%BB%93%E5%90%88%E4%BA%B2%E5%92%8C%E5%8A%9B" }, "mcp": "https://mcp.mdexa.com/mcp", "anonymous_calls_per_minute": 20, "guide": "https://mdexa.com/zh/agents.md", "faq": "https://mdexa.com/zh/developers/faq/", "similar": [ { "name": "IMCS-21", "url": "https://mdexa.com/zh/datasets/imcs-21/", "json": "https://mdexa.com/zh/datasets/imcs-21.json" }, { "name": "CMtMedQA", "url": "https://mdexa.com/zh/datasets/cmtmedqa/", "json": "https://mdexa.com/zh/datasets/cmtmedqa.json" }, { "name": "DISC-Med-SFT", "url": "https://mdexa.com/zh/datasets/disc-med-sft/", "json": "https://mdexa.com/zh/datasets/disc-med-sft.json" } ] } }