weigoss / cmrc2018 Goto Github PK

CMRC 2018 Official Website (Chinese only)：https://cmrc2018.hfl-rc.com/

The Second Evaluation Workshop on Chinese Machine Reading Comprehension was succesfully ended. The evaluation committee had decided to continue to accept submissions to further evaluations on the hidden test set and challenge set.

CMRC 2018 Public Datasets: https://worksheets.codalab.org/worksheets/0x92a80d2fab4b4f79a2b4064f7ddca9ce

Submission Guidelines: https://worksheets.codalab.org/worksheets/0x96f61ee5e9914aee8b54bd11e66ec647/

Open Challenge Leaderboard: https://hfl-rc.github.io/cmrc2018/open_challenge/

2019/8/14 Our dataset is accepted as a short paper by EMNLP-IJCNLP 2019!

2019/3/29 We provide SQuAD-style CMRC 2018 datasets, which is exactly the same with the format for SQuAD, see CodaLab link

2018/12/7 Open Challenge has been announced.

2018/10/18 System overview paper was out.

2018/5/7 Training and development data has been released.

2018/3/13 Trial data has been released.

2018/2/1 The trial data will be available on March 5, 2018.

If you are participating CMRC 2018, please download data and evaluation script through CodaLab.

System overview: https://arxiv.org/abs/1810.07366

If you wish to use this data in your research, please cite:

@InProceedings{cui-emnlp2019-cmrc2018,
  author = 	"Cui, Yiming and Liu, Ting and Che, Wanxiang and Xiao, Li and Chen, Zhipeng and Ma, Wentao and Wang, Shijin and Hu, Guoping",
  title = 	"A Span-Extraction Dataset for Chinese Machine Reading Comprehension",
  booktitle = 	"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing",
  year = 	"2019",
  publisher = 	"Association for Computational Linguistics"
}

ISLRN: 013-662-947-043-2

http://www.islrn.org/resources/resources_info/7952/

Follow Joint Laboratory of HIT and iFLYTEK Research (HFL) on WeChat.

Any problems? Feel free to concat us.

E-MAIL： [email protected]