Semantic Extraction with Wide-Coverage Lexical Resources

Portability and domain independence are critical challenges for Natural Language Processing (NLP) systems. Semantic Extraction is an NLP task that pertains to the assignment of semantic bindings to short units of text (usually sentences). NLP problems such as Information Extraction, Question Answering Systems and Text Classification Systems should benefit from Semantic Extraction. I have used two manually-built knowledge bases (WordNet and FrameNet) to automate Semantic Extraction. My prototype system shows promising results when compared to existing algorithms. As part of this work, I compiled a large and semantically-rich information extraction pattern set and lexicon, and will make this available to the NLP community in the near future.