A Generative Knowledge Question Answering Method Based on Representation Learning and Multilayer Overlay Mechanism

Abstract

The invention relates to a generative knowledge question answering method based on representation learning and multi-layer covering mechanism, and belongs to the technical field of artificial intelligence and natural language processing. In the knowledge base of the knowledge question answering system, the fact that the facts cannot be effectively represented will reduce the ability to find the correct answer. In the generative question answering task, the model will fall into a certain mode and cannot jump out, or repeatedly generate the generated vocabulary in a certain mode. For technical problems that lead to the decline of answer readability, first build a generative knowledge question answering model, use the Seq2Seq framework, combine the attention mechanism, CopyNet model, GenQA model and Coverage coverage mechanism, parse the question through the encoder, and query the knowledge base. information, use the decoder to generate the answer. In a given scenario, a complete sentence can be generated, the answer contains correct knowledge, and the generated answer has fluency, consistency and correctness. All achieved good results.

Description

technical field [0001] The invention relates to a generative knowledge question answering method, in particular to a generative knowledge question answering method based on representation learning and a multi-layer covering mechanism, and belongs to the technical field of artificial intelligence and natural language processing. Background technique [0002] Question Answering System (QA) is an advanced form of information retrieval system, which can use accurate and concise natural language to answer questions raised by users in natural language. The need to obtain information. Question answering system is a research direction in the field of artificial intelligence and natural language processing that has attracted much attention and has broad prospects for development. [0003] The task of the knowledge question answering system is to directly search and infer the matching answer in the knowledge base according to the semantics of the user's question. This task is also c...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to overcome the defects of the prior art. In order to solve the knowledge base of the knowledge question answering system, facts cannot be effectively represented, which reduces the ability to find the correct answer, and the model in the generative question answering task often falls into a certain mode and cannot jump out. , or repeating the generated vocabulary in a certain mode, resulting in a technical problem that the readability of the answer is reduced. A generative knowledge question answering method based on representation learning and multi-layer coverage mechanism is proposed.

Images