Knowledge base question and answer entity linking method and system based on similarity

Abstract

The invention belongs to the technical field of data processing, and discloses a knowledge base question and answer entity linking method and system based on similarity, and the method comprises the steps that entities in a question are recognized through a deep learning method, and the end-to-end entity linking is carried out; in the candidate entity generation stage, named entity identificationis carried out by using a Bert feature extraction network and a BiLSTM-CRF sequence labeling model to generate candidate entities; in the disambiguation stage of the candidate entities, relational words in the questions are extracted through a certain rule and sorted according to the similarity between the relational words and the candidate relations, and the question and answer time of the knowledge base is shortened. According to the method, an end-to-end thought is applied to knowledge base questioning and answering, knowledge base questioning and answering questions are combined with an advanced computer technology, and named entity recognition is performed by using a Bert feature extraction network and a BiLSTM-CRF sequence labeling model to generate candidate entities. According to the method, the problem that the candidate entities are polysemous in one word is relieved, and the entity linking accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a similarity-based knowledge base question answering entity linking method and system. Background technique [0002] At present, with the rapid development of artificial intelligence, knowledge base question answering has become a research hotspot in the computer field. Knowledge base-oriented question answering refers to natural language questions raised by users. By determining the entities in the question, the query links to the corresponding knowledge base. Entity, find and return the answer through the relationship connected with the entity in the knowledge base, which can be mainly divided into two parts: entity link and relationship detection. Entity linking is the core technology in the fields of machine translation, information retrieval, and topic discovery and tracking. During machine translation, the higher the accuracy of entity linking in sentenc...

AI Technical Summary

Problems solved by technology

Obviously, the disadvantage of statistical model-based methods is the lack of consideration of entity semantics

[0007] (1) The recognition effect is very dependent on prior knowledge and manually defined rule templates, which consumes a lot of human resources

[0008] (2) The problem of gradient disappearance is prone to occur, causing the network to only learn information that is relatively close to the current moment

[0009] (3) Although the accuracy of entity recognition has been effectively improved to a certain extent, it cannot solve the problem of polysemy of entity words, nor can it take into account the accuracy and recall of entity links

Its potential applications include information extraction, information retrieval, and knowledge base population, but this task is challenging due to name variations and entity ambiguity

Images