Abstract
It is a challenging task to automatically excavate new words from huge amounts of domain-specific corpus. This paper proposed a new phrase mining method based on a fast-text model. With existing terminology and iterative computing framework, this method can extract high-quality domain terms from a given domain-specific corpus. Experiments on geographic corpus show that mining results of this method are more accurate compared with that of the traditional unsupervised mining method, with an accuracy of 68.6% in the top 500 candidates. Meanwhile, the scoring system is more reasonable and effective. In general, this new word mining method can effectively utilize external knowledge and save costs of manual labeling. It is more practical and important to the construction and expansion of the glossary.
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 callMore From: International Journal of Asian Language Processing
Disclaimer: 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.
