(ALMOST) AUTOMATIC SEMANTIC FEATURE EXTRACTION FROM TECHNICAL TEXT

摘要

Acquisition of semantic information is necessary for proper understanding of natural language text. Such information is often domain-specific in nature and must be acquired from the domain. This causes a problem whenever a natural language processing (NLP) system is moved from one domain to another. The portability of an NLP system can be improved if these semantic features can be acquired with limited human intervention. This paper proposes an approach towards (almost) automatic semantic feature extraction.