A Fast, Accurate Deterministic Parser for Chinese

We present a novel classifier-based deterministic parser for Chinese constituency parsing. Our parser computes parse trees from bottom up in one pass, and uses classifiers to make shift-reduce decisions. Trained and evaluated on the standard training and test sets, our best model (using stacked classifiers) runs in linear time and has labeled precision and recall above 88% using gold-standard part-of-speech tags, surpassing the best published results. Our SVM parser is 2-13 times faster than state-of-the-art parsers, while producing more accurate results. Our Maxent and DTree parsers run at speeds 40-270 times faster than state-of-the-art parsers, but with 5-6% losses in accuracy.

• Type: Conference
• Year: 2006
• Where: ACL
• Authors: Mengqiu Wang, Kenji Sagae, Teruko Mitamura
• Keywords: ACL 2006, ACL 2007, Parser Computes Parse, Parsers, State-of-the-art Parsers