Modal Expressions in Natural Language Sentence and Their Similarity

Abstract

This paper is concerned with the treatment of modal information in natural language processing (NLP). Modal information, which fleshes out the kernel sentence, providing temporal, interpersonal, contingent or subjective information, i.e., polarity, tense, aspect, mood, modality in narrow sense, specific kinds of speaker’s judgment or attitude, etc plays an important role especially in discourse understanding, man-machine dialogue, inference system, etc. On the other hand, It is important for future NLP systems to formulate the semantic similarity of natural language expressions. In particular, paraphrasing, full text information retrieval, example-based MT and document compression technology require the effective similarity criterion for linguistic expressions. In this paper, first, we discuss the meaning of Japanese sentence-final modality expressions (ME) and second, we present similarity rules.

Resources

Details