Universal Chinese dialogue generating method using two-stage compound template

Abstract

The invention relates to a general Chinese two-stage hybrid mold conversational language generation method, which involves the artificial intelligent natural language generating technique, especially generating the Chinese language with conversational characteristics according to the intrinsic expression of the language. The method divides the Chinese clause into two levels, which are sentence and phrase. Each level is generated by different mold. That is generating phrase according to the phrase mold, then combining the phrase mold to sentence according to the requirement of the sentence mold. In this way, the sentence is generated. The method is capable of providing the information needed by various types of the generated sentences, making use of the language behavior expression. Exacting language environment information assisted to generate the sentence makes the sentence more suitable for the conversational language environment. The algorithm independent of the task is easy to be transplanted.

Description

technical field [0001] The invention relates to artificial intelligence natural language generation technology, in particular to generating Chinese language with spoken language characteristics according to internal expressions of speech. Background technique [0002] Spoken language generation methods refer to computer software systems that are an integral part of task-oriented dialogue systems that can generate natural language suitable for spoken dialogue from the internal expressions of speech. [0003] In summary, existing natural language generation methods can be classified into four categories: [0004] 1. The method of encapsulating text: An encapsulating text is a pre-defined string, which is written when the system is designed. The system stores a set of strings and trigger conditions for each string. One of these will be shown when triggered. Such strings are static and are presented to the user unchanged. [0005] 2. Template-based approach: A template is a ...

AI Technical Summary

Problems solved by technology

The method of linguistics utilizes the syntactic characteristics of sentences, such as tense, number, and subject-predicate consistency. Although the generated sentences are relatively flexible, because Chinese is not an inflectional language, it lacks formal changes and surface constraints of syntax, so linguistics The method is obviously not suitable for the generation task of Chinese

Sentences generated by non-linguistic methods lack flexibility, are difficult to adapt to the characteristics of spoken language, and the task of maintaining templates is heavy.