Abstract
New word detection is of great significance for Chinese text information processing, which directly affects the capabilities of word segmentation, information retrieval and automatic translation. Focusing on the problem of Chinese new word detection, this paper proposes an independence-testing-based detection approach with no need of prior information. The paper analyzes statistical characteristics of new words in Chinese texts, uses statistical hypothesis testing to infer the correlations between adjacent semantic units, and proposes an iterative algorithm to detect new words gradually. Our algorithm is evaluated on both large-scale corpus and short news texts. Experimental results show that this approach can effectively detect new words from all kinds of news.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
