{"adoption": {"forks": 489, "observed_at": "2026-08-28T04:06:09.893366+00:00", "stars": 2056}, "canonical_url": "https://ross.abutalabs.com/products/dialog_corpus", "card": {"archived": false, "artifact_type": "dataset", "description": "用于训练中英文对话系统的语料库 Datasets for Training Chatbot System", "domain": ["chatbots", "machine-learning"], "enriched": true, "function": ["nlp", "chatbot", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["candlewill/Dialog_Corpus"], "name": "candlewill/Dialog_Corpus", "platform": ["python", "cross-platform"], "pushed_at": "2020-09-23T21:06:45+00:00", "repo": "candlewill/Dialog_Corpus", "stars": 2056, "tags": ["dialog-corpus", "chinese-nlp", "conversation-datasets", "awesome-list", "training-data", "natural-language-processing"], "topics": ["dataset", "dialog", "system", "corpus", "chatbot"], "urls": [], "use_cases": ["find training data for a Chinese chatbot", "download movie subtitle dialogue corpora", "get QA pairs for a retrieval-based dialog system", "collect SMS conversation data for NLP research", "build a seq2seq conversation model with open datasets"], "what_it_is": "A curated collection of links to Chinese and English dialogue corpora for training chatbot systems, including movie subtitles, SMS corpora, QA pairs, and community chat logs. It is primarily an index of publicly available datasets rather than a software tool.", "when_to_avoid": ["you need a maintained, license-clear dataset with guaranteed quality", "you need actual data hosted in this repo rather than external links", "you need modern instruction-tuning or LLM training data"], "when_to_choose": ["you need open dialog datasets for Chinese or English chatbot training", "you want a starting index of conversation corpora instead of scraping data yourself"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dialog_corpus", "repo": "candlewill/Dialog_Corpus", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.893366+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:57:11.990067+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "03ce341fcaf67bb934c8b28a608f840f98e3b0318e52d4b142bddebb088f247d", "fetched_at": "2026-08-28T04:06:09.893366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/candlewill/Dialog_Corpus"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3459, "days_push": 2170, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}