@inproceedings{L16-1244,
 abstract = {This paper provides a new method to correct annotation errors in a treebank. The previous error correction method constructs a pseudo parallel corpus where incorrect partial parse trees are paired with correct ones, and extracts error correction rules from the parallel corpus. By applying these rules to a treebank, the method corrects errors. However, this method does not achieve wide coverage of error correction. To achieve wide coverage, our method adopts a different approach. In our method, we consider that an infrequent pattern which can be transformed to a frequent one is an annotation error pattern. Based on a tree mining technique, our method seeks such infrequent tree patterns, and constructs error correction rules each of which consists of an infrequent pattern and a corresponding frequent pattern. We conducted an experiment using the Penn Treebank. We obtained 1,987 rules which are not constructed by the previous method, and the rules achieved good precision.
},
 address = {Portorož, Slovenia},
 author = {Kanta Suzuki and Yoshihide Kato and Shigeki Matsubara},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {1540--1545},
 publisher = {European Language Resources Association (ELRA)},
 title = {Correcting Errors in a Treebank Based on Tree Mining},
 url = {https://www.aclweb.org/anthology/L16-1244},
 year = {2016}
}