Automatic Semantic Sequence Extraction from Unrestricted Non-Tagged Texts

Mophological processing, syntactic parsing and other useflfl tools have been proposed in the field of natural language processing(NLP). Many of those NLP tools take dictionary-based approaches. Thus these tools are often not very efficient with texts written in casual wordings or texts which contain maw domain-specific terms, because of the lack of vocabulary. In this paper we propose a simple method to obtain domain-specific sequences from unrestricted texts using statist;ical information only. This method is language-independent. We had experiments oil sequence extraction on email l;exts in Japanese, and succeeded in extracting significant semantic sequences in the test corpus. We tried morphological parsing on the test corpus with ChaSen, a Japanese dictionary-based morphological parser, and examined our system's efficiency in extraction of semantic sequences which were not recognized with ChaSen. Our system detected 69.06% of the unknown words correctly.

• Type: Conference
• Year: 2000
• Where: COLING
• Authors: Shiho Nobesawa, Hiroaki Saito, Masakazu Nakanishi
• Keywords: COLING 2000, COLING 2008, Maw Domain-specific Terms, Semantic Sequences, Test Corpus