Word Based Chinese Semantic Role Labeling with Semantic Chunking
Weiwei Ding, Baobao Chang · International Journal of Computer Processing Of Languages · 2009
Recently, with the development of Chinese semantically annotated corpora, e.g. the Chinese Proposition Bank, the Chinese role labeling (SRL) has been boosted. However, the Chinese SRL researchers now focus on the transplant of existing statistical machine learning methods which have been proven to be effective on English. In this paper, we have established a word based Chinese SRL system, which is quite different from the previous based ones. We use semantic to represent our new method. Semantic chunking is named because of its similarity with syntactic chunking. The difference is that chunking is used to identify and classify the chunks, i.e. the roles, only with the word-level information. Based on chunking, the process of SRL is changed from parsing — role identification — role classification, to semantic chunk identification — chunk With the elimination of the stage, the SRL task can get rid of the dependency on parsing, which is the bottleneck both of speed and precision. The experiments have shown that the chunking based method outperforms previously best-reported results on Chinese SRL, if the word segmentation and part-of-speech (POS) tagging are both correct. On the automatic word segmentation and POS tagging, our method decreases a little. The greatest advantage of chunking method is that it saves a large amount of time. Besides these, we also carry out some experiments only for role classification. These experiments have shown that only with the word-level features, the performance of role classification can still be very high, which proves that the syntactic structural information is not indispensable.