Negative Sentence and "F-V-M" Analysis

Although natural language processing (NLP) technology has brought great help to human, it also produces many negative sentences, which has gradually become a big problem to the development of NLP and applications. Now it's an important and urgent task for us to deal with various negative sentences. As a starting study, this paper puts forward a new understanding of the concept of negative sentence and a natural language understanding (NLU) based method of "form-value-meaning" (F-V-M) analysis, which could check the reliability, or possible errors of negative sentences in open application domains with the help of pragmatic information, fuzzy set, online related corpus acquisition, knowledge base building and updating. An initial implementation is also done for speech recognition (SR) negative sentences in the domain of hotel. Testing results have shown its feasibility.