ymcui/cmrc2018
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
The dataset comprises ~20k human-annotated Chinese passages with span-based answer annotations, distributed via HuggingFace's `datasets` library for direct integration with modern NLP frameworks. Evaluation occurs through CodaLab worksheets with separate hidden test and challenge sets, enabling standardized benchmarking beyond the public CLUE leaderboard version. The repository also hosts an open leaderboard tracking state-of-the-art span-extraction models on Chinese MRC tasks.
451 stars. No commits in the last 6 months.
Stars
451
Forks
87
Language
Python
License
CC-BY-SA-4.0
Category
Last pushed
Jun 15, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ymcui/cmrc2018"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
princeton-nlp/DensePhrases
[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval...
thunlp/MultiRD
Code and data of the AAAI-20 paper "Multi-channel Reverse Dictionary Model"
IndexFziQ/KMRC-Papers
A list of recent papers regarding knowledge-based machine reading comprehension.
danqi/rc-cnn-dailymail
CNN/Daily Mail Reading Comprehension Task
declare-lab/CIDER
This repository contains the dataset and the pytorch implementations of the models from the...