@inproceedings{L16-1243,
 abstract = {Treebanks are important resources for researchers in natural language processing, speech recognition, theoretical linguistics, etc. To strengthen the automatic processing of the Vietnamese language, a Vietnamese treebank has been built. However, the quality of this treebank is not satisfactory and is a possible source for the low performance of Vietnamese language processing. We have been building a new treebank for Vietnamese with about 40,000 sentences annotated with three layers: word segmentation, part-of-speech tagging, and bracketing. In this paper, we describe several challenges of Vietnamese language and how we solve them in developing annotation guidelines. We also present our methods to improve the quality of the annotation guidelines and ensure annotation accuracy and consistency. Experiment results show that inter-annotator agreement ratios and accuracy are higher than 90\% which is satisfactory.
},
 address = {Portorož, Slovenia},
 author = {Quy Nguyen and Yusuke Miyao and Ha Le and Ngan Nguyen},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {1532--1539},
 publisher = {European Language Resources Association (ELRA)},
 title = {Challenges and Solutions for Consistent Annotation of Vietnamese Treebank},
 url = {https://www.aclweb.org/anthology/L16-1243},
 year = {2016}
}