Data-driven learning based on shift reduce parsing algorithms has emerged dependency parsing and shown excellent performance to many Treebanks. In this paper, we investigate the e...
The Context-Free backbone of some natural language analyzers produces all possible CF parses as some kind of shared forest, from which a single tree is to be chosen by a disambigu...
In Japanese dependency parsing, Kudo's relative preference-based method (Kudo and Matsumoto, 2005) outperforms both deterministic and probabilistic CKY-based parsing methods....
We implement a Korean syntactic analyzer which decreases many ambiguities in syntax parse trees using segmentation and semantic connection units. We use dependency grammar for par...
A major concern in corpus based approaches is that the applicability of the acquired knowledge may be limited by some feature of the corpus, in particular, the notion of text `dom...