A method for extracting hypernym-hyponym relationship based on concept definition and data enhancement

By combining bidirectional LSTM, BERT, and attention mechanisms, and utilizing concept definition and data augmentation methods, the problem of ignoring semantic relationships in existing technologies is solved, thereby improving the accuracy and robustness of hyponym extraction.

CN116502647BActive Publication Date: 2026-06-09ANHUI UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ANHUI UNIV
Filing Date
2023-03-06
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing technologies ignore the semantic relationships in concept definitions when extracting hierarchical relationships, resulting in poor prediction performance.

Method used

We adopt a concept definition and data augmentation-based approach, combining bidirectional LSTM with the pre-trained language model BERT. We obtain concept vectors and offset vectors through an attention mechanism, train the model using the cross-entropy loss function, and perform data augmentation by combining Hearst patterns to construct a hyper-hyper-subordinate relationship prediction model.

Benefits of technology

It improves the accuracy and robustness of extracting hierarchical relationships, better captures deep semantic information in concept definitions, and enhances the model's predictive performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116502647B_ABST
    Figure CN116502647B_ABST
Patent Text Reader

Abstract

The application provides a hypernym-hyponym relation extraction method based on concept definition and data enhancement, which comprises the following steps: extracting concept pairs from natural text by using a keyword extraction technology, constructing concept triples based on the concept pairs and the hypernym-hyponym relations corresponding to the concept pairs, and taking the set of concept triples as a training data set; obtaining concept vectors in each triple in the training data set, offset vectors between the concept vectors, and vectors of concept definitions; constructing a hypernym-hyponym relation prediction model with the training data set as the input and the fused vectors of the offset vectors between the concept vectors, the concept vectors, and the vectors of concept definitions as the output, training the hypernym-hyponym relation prediction model according to the training data set and the fused vectors; obtaining a to-be-predicted concept triple in a test text, inputting the to-be-predicted concept triple into the trained hypernym-hyponym relation prediction model, and predicting whether the to-be-predicted concept triple has a hypernym-hyponym relation according to the output components.
Need to check novelty before this filing date? Find Prior Art