Title :
Using language rules to improve the performance of word segmentation
Author :
Rong Sun ; Wen Zhou ; Zongtian Liu
Author_Institution :
Shanghai Univ., Shanghai, China
Abstract :
Due to the disadvantage of the word segmentation tool in the aspect of the accuracy of word segmentation and speech tagging, it has harmful effects to the further research work. So this paper proposes a method based on the results of word segmentation to utilize language rules, which has been defined and described in Event Ontology, to verify and correct them. Experimental results show that compared with the method of only using word segmentation tool, the method of using language rules has a better performance.
Keywords :
natural language processing; ontologies (artificial intelligence); text analysis; event ontology; language rules; speech tagging; word segmentation tool; Accuracy; Computers; Dictionaries; Hidden Markov models; Ontologies; Sun; Tagging; Event; Event Ontology; Language Rule; Performance; Word Segmentation;
Conference_Titel :
Image and Signal Processing (CISP), 2013 6th International Congress on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4799-2763-0
DOI :
10.1109/CISP.2013.6743944