Current Proceedings on Technology
Yazarlar: Jiong Yang, Jie Feng, Jiong Yang
Konular:-
Anahtar Kelimeler:Natural language processing,Extmining,Ioinformatics
Özet: A natural language parser is a program that works out the grammatical structure of sentences. It is important for knowledge discovering and text mining. Here we presented several semantic parsers, which could discover the semantic dependency relations in a sentence. The dependency output of the Link Grammar parser is similar to that of the Stanford parser. Its performance is comparable to the Stanford PCFG parsing model, and is more than three times faster than the Stanford lexicalized model. Much further work will be needed. Through the comparisons, we find the Stanford parser is the best of the three on most aspects.