System for reading robot to perform automatic questioning and answerin and application method thereof

Abstract

The invention discloses a method and a system for a reading robot to perform automatic questioning and answering. The system comprises a question type analysis module, a word similarity matching module, a paragraph topic sentence and author viewpoint sentence extraction module and an answer sentence extraction module, and firstly proposes a method of analyzing question types according to general questioning and answering characteristics and then performing linear interpolation, thereby effectively filling in the blank of analyzing the question types only according to question sentences; according to the method, some answer candidate sentences which are not matched with question keywords and frameworks can be recalled by extracting paragraph theme sentences and author viewpoint sentences; according to the invention, intelligent answering for questioning and answering purposes in reading understanding can be realized, and the answering rate of automatic questioning and answering is effectively improved; the method provided by the invention can also be applied to natural language processing tasks such as text implication, automatic abstract, complex problem solving and the like.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a method and system for automatic question answering by a reading robot. Background technique [0002] In recent years, question answering technology research has received extensive attention. At present, relatively mature question answering systems include Start developed by the Artificial Intelligence Laboratory of MIT, AnswerBus developed by the University of Michigan, Siri developed by Apple, and Cotana developed by Microsoft. Some robots with intelligent question-answering technology as the core have also been launched in China, such as Microsoft's Xiaobing, Baidu's Xiaodu, etc., but the research on question-answering based on reading comprehension is far from enough. [0003] At present, there are mainly two research directions based on retrieval model and based on deep learning. Retrieval methods based on traditional statistical features mainly rely on semantic ...

AI Technical Summary

Problems solved by technology

[0004] At present, the method based on retrieval model and deep learning has achieved good results on general reading comprehension problems, but the effect on Chinese reading comprehension questions in the college entrance examination is not satisfactory. This is because the reading comprehension problems in the college entrance examination are more complicated. Requires deep semantic understanding and reasoning about questions and background material

In addition, although deep learning-based methods can automatically learn features, they require sufficient data for training.

Images