Novel answer selection model based on GRU attention mechanism

Abstract

Answer selection (AS) is an important subtask in question and answer system design, and the problem is mainly solved by using a deep learning method at present. A traditional attention mechanism is more biased to the following state characteristics, and an internal attention mechanism is provided based on the following state characteristics, so that the problem of weight distribution deviation isavoided. However, a model does not screen the input information, which results in more noise contained in the candidate output hidden state. The invention relates to an algorithm for an answer selection model of a question and answer system. The invention has the following effects: (1) an input gate in front of an attention model is added in a GRU to filter useless information; (2) an answer selection model is improved in the question and answer system by using the new attention mechanism, and accuracy is improved compared with that of an original GRU-based internal attention mechanism model;and (3) the method provided by the invention is greatly improved in the aspects of accuracy, algorithm stability and the like, and can be better suitable for practical engineering work.

Description

technical field

[0001] The invention relates to the field of natural language processing, that is, an algorithm for selecting the optimal reply in an answer selection model of a question answering system. Background technique

[0002] Answer selection (Answer selection, AS) is an important sub-task in the design of question answering system. Its function is to select the best answer from a series of candidate responses for a given question. The accuracy of answer selection during dialogue plays a key role in the performance of question answering systems. In the past few years, answer selection has received a lot of attention. Among them, the use of neural network models to solve answer selection tasks has achieved great success. However, when the semantic vector is generated by the cyclic neural network, the question and the answer are encoded separately, and the information related to the question in the answer is ignored, resulting in the generated answer semantic vector...

Images