Learn More
In this paper, we present a three-step multilingual dependency parser based on a deterministic shift-reduce parsing algorithm. Different from last year, we separate the root-parsing strategy as sequential labeling task and try to link the neighbor word dependences via a near neighbor parsing. The outputs of the root and neighbor parsers were encoded as(More)
Phrase pattern recognition (phrase chunking) refers to automatic approaches for identifying predefined phrase structures in a stream of text. Support vector machines (SVMs)-based methods had shown excellent performance in many sequential text pattern recognition tasks such as protein name finding, and noun phrase (NP)-chunking. Even though they yield very(More)
The most important factor of classification for improving classification accuracy is the training data. However, the data in real-world applications often are imbalanced class distribution, that is, most of the data are in majority class and little data are in minority class. In this case, if all the data are used to be the training data, the classifier(More)
Data-driven learning based on shift reduce parsing algorithms has emerged dependency parsing and shown excellent performance to many Tree-banks. In this paper, we investigate the extension of those methods while considerably improved the runtime and training time efficiency via L 2-SVMs. We also present several properties and constraints to enhance the(More)
In Chinese, most of the language processing starts from word segmentation and part-of-speech (POS) tagging. These two steps tokenize the word from a sequence of characters and predict the syntactic labels for each segmented word. In this paper , we present two distinct sequential tagging models for the above two tasks. The first word segmentation model was(More)