Research Area:  Machine Learning

Abstract:

Machine reading comprehension has been a research focus in natural language processing and intelligence engineering. However, there is a lack of models and datasets for the MRC tasks in the anti-terrorism domain. Moreover, current research lacks the ability to embed accurate background knowledge and provide precise answers. To address these two problems, this paper first builds a text corpus and testbed that focuses on the anti-terrorism domain in a semi-automatic manner. Then, it proposes a knowledge-based machine reading comprehension model that fuses domain-related triples from a large-scale encyclopedic knowledge base to enhance the semantics of the text. To eliminate knowledge noise that could lead to semantic deviation, this paper uses a mixed mutual attention mechanism among questions, passages, and knowledge triples to select the most relevant triples before embedding their semantics into the sentences. Experiment results indicate that the proposed approach can achieve a 70.70% EM value and an 87.91% F1 score, with a 4.23% and 3.35% improvement over existing methods, respectively.

Keywords:  
Machine reading comprehension
Anti-terrorism domain
Knowledge embedding
Knowledge attention
Mutual attention

Author(s) Name:  Feng Gao, Jin Hou, Jinguang Gu, Lihua Zhang

Publisher name:  MIT Press

DOI:  10.1162/dint_a_00210

Volume Information:  Volume 5 , (2023)

Paper Link:   https://direct.mit.edu/dint/article/5/3/685/117370