@inproceedings{8612e375354c48849620caef750c4199,
title = "M-CNER: A corpus for Chinese named entity recognition in multi-domains",
abstract = "In this paper, we present a new corpus for Chinese Named Entity Recognition (NER) from three domains: human-computer interaction, social media, and e-commerce. The annotation procedure is conducted in two rounds. In the first round, one sentence is annotated by more than one persons independently. In the second round, the experts discuss the sentences for which the annotators do not make agreements. Finally, we obtain a corpus which have five data sets in three domains. We further evaluate three popular models on the newly created data sets. The experimental results show that the system based on Bi-LSTM-CRF performs the best among the comparison systems on all the data sets. The corpus can be used for further studies in research community.",
keywords = "Chinese Data Set, Information Extraction, Named Entity Recognition",
author = "Qi Lu and Yang, \{Yao Sheng\} and Zhenghua Li and Wenliang Chen and Min Zhang",
note = "Publisher Copyright: {\textcopyright} LREC 2018 - 11th International Conference on Language Resources and Evaluation. All rights reserved.; 11th International Conference on Language Resources and Evaluation, LREC 2018 ; Conference date: 07-05-2018 Through 12-05-2018",
year = "2018",
language = "英语",
series = "LREC 2018 - 11th International Conference on Language Resources and Evaluation",
publisher = "European Language Resources Association (ELRA)",
pages = "4457--4461",
editor = "Nicoletta Calzolari and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga",
booktitle = "LREC 2018 - 11th International Conference on Language Resources and Evaluation",
}