Machine reading understanding method for guiding attention based on knowledge

Abstract

The invention discloses a machine reading understanding method for guiding attention based on knowledge. The method comprises the following steps of: (1) obtaining a word vector of a sequence by usinga pre-trained word embedding matrix; (2) modeling the context information of each word in the text by using a bidirectional GRU network; (3) inputting the context representation of the question intoa one-way GRU network as an initial hidden layer state, wherein the GRU network iteratively executes a search step by using an attention-based look-back mechanism so as to collect information possiblyused for predicting answers in the article; (4) taking external knowledge as long-term memory, adding the external knowledge into a replaying mechanism, guiding the focus of attention in the replaying process, and redistributing attention scores by the model; and (5) obtaining a predicted answer at the output end of the one-way GRU network through the pointer network. The method is an end-to-endmodel, and data preprocessing, except for pre-trained word vectors, in an unlabeled corpus set is not needed, so that the method can be widely applied to reading understanding of different languages and fields.

Description

technical field [0001] The invention relates to natural language processing, in particular to a machine reading comprehension method based on knowledge guiding attention. Background technique [0002] Natural Language Processing (NLP) is an interdisciplinary subject integrating linguistics and computer science. Reading comprehension (Reading Comprehension) is a fundamental task in natural language processing, usually by asking the system to answer questions, inferring answers from a given text or context. With the advent of the Internet age, the information on the Internet has exploded, including text data in various languages ​​and forms, such as news from Sina and Daily Mail, articles from Baidu and Wikipedia, Zhihu and Answers from question-and-answer communities like Quora. These corpora become the basis for constructing large-scale machine reading comprehension datasets. Teaching machines to read, process and understand human language is one of the core tasks of natu...

AI Technical Summary

Problems solved by technology

When people read and understand the content of an article, the process of reasoning is almost everywhere. Without reasoning, people cannot fully understand the content, and the same is true for machines.

Images