Textbook question answering method and system based on multi-level attention

By using a multi-level attention model, the accuracy and interpretability issues in textbook question-and-answer tasks are resolved, achieving higher accuracy and answer interpretability, and making it suitable for question-and-answer in natural science textbooks.

CN116775836BActive Publication Date: 2026-05-22XI AN JIAOTONG UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202310776007.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-06-28
Publication Date
2026-05-22
Estimated Expiration
2043-06-28

AI Technical Summary

Technical Problem

Existing question-answering models perform poorly on textbook question-answering tasks, especially due to input length limitations and differences in educational corpora, resulting in low accuracy and a lack of interpretability.

Method used

We employ a textbook text question-answering method based on multi-layer attention. The first-layer attention model performs intra-sentence self-attention calculation and pooling, while the second-layer attention model performs self-attention calculation between paragraphs and between paragraphs and questions. Combined with a two-layer network classifier, we select the correct answer and provide text support with strong interpretability.

Benefits of technology

It improved the accuracy of textbook Q&A tasks, especially in natural science content, and the answers were more explanatory.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

A textbook text question and answer method and system based on multi-level attention, the method comprising: inputting the question text and the corresponding chapter context paragraph into the first attention model after tokenization and coding, performing self-attention calculation and pooling within the sentence to obtain the sentence representation vector; calculating the cosine similarity of the question sentence representation vector and the representation vector of all context paragraph sentences, retaining only the representation vector corresponding to the sentence with the maximum similarity of each paragraph as the context representation vector of each paragraph corresponding to the question; inputting the question and the context representation vector of each paragraph corresponding to the question into the second attention model, performing self-attention calculation and pooling between the paragraphs and the question to obtain the answer representation vector corresponding to the question as the input of the classifier; outputting the answer options by the classifier, and obtaining the context paragraph of the answer text corresponding to the chapter. The application can select more accurate answer options for textbook text questions.
Need to check novelty before this filing date? Find Prior Art