Entity disambiguation method and device, readable storage medium and electronic device

Abstract

The invention discloses an entity disambiguation method and device, a readable storage medium and an electronic device. The method is characterized by obtaining the vector of an entity through the word vector of each word in the entity to thereby carry out the disambiguation according to all vectors in the entity, and comprises the following steps of firstly, inputting a to-be-processed text comprising at least two entities into an entity extraction language model for entity extraction to obtain the entities included in the to-be-processed text; inputting the to-be-processed text into a bidirectional language model for processing to obtain a word vector sequence of the to-be-processed text; obtaining a word vector of each word in any entity; calculating to obtain a word vector of any entity according to the word vector of each character in any entity; calculating the similarity between every two entities according to the word vector of each entity; and finally, clustering the entitiesaccording to the similarity between every two entities in the to-be-processed text to realize the entity disambiguation. According to the scheme of the embodiment, the entity disambiguation accuracy can be improved.

Description

technical field [0001] The present application relates to the field of natural language processing, in particular, to an entity disambiguation method, device, readable storage medium and electronic equipment. Background technique [0002] Text is organized by a large number of words, and there are usually a large number of ambiguous entity words in the words that make up the text. After entity disambiguation is performed on the text, information extraction and text summary construction can be realized according to the results of entity disambiguation. The accuracy of entity disambiguation also directly affects the accuracy of information extraction. [0003] In the prior art, when performing entity disambiguation, one way is to use a large amount of relevant texts for word vector training to obtain a word embedding matrix, and extract entities from the text to be processed. After the entities extracted from the text to be processed are converted into vectors, these entities...

AI Technical Summary

Problems solved by technology

In addition, new words that do not exist in the word embedding matrix cannot be converted into vectors

Therefore, there is a large error in the result of disambiguation using this entity disambiguation method

Images