Research on Discourse Coherence based on the Analysis Model of Event Chain from the Perspective of Computational Linguistics

Abstract

With the rapid development of network technology, natural language processing has also entered a boom period. Probability and data-driven methods have been widely used in natural language processing. The need for people to extract and retrieve information from the Internet is also increasing, and more and more researchers are trying to use computers to process content related to discourse coherence. Based on the event chain of the text semantic structure representation, this paper proposes a text semantic structure representation model, on the basis of which, text coherent resources can be used for the task of text semantic analysis. Event chain is a necessary condition for discourse coherence, which can be transformed into a computable event chain analysis problem, and can be further formalized as discourse-oriented partial dependency analysis of sentences.