Next Article in Journal
Innovative Quality Assessment of Pavement Subgrades Using the Glegg Impact Soil Tester
Previous Article in Journal
Analysis of the Effects of Parameters on the Performance of Resonators Based on a ZnO/SiO2/Diamond Structure
Previous Article in Special Issue
A Novel Computationally Efficient Approach for Exploring Neural Entrainment to Continuous Speech Stimuli Incorporating Cross-Correlation
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 14
Issue 2
10.3390/app14020875
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Exploring the Cognitive Neural Basis of Factuality in Abstractive Text Summarization Models: Interpretable Insights from EEG Signals

by
Zhejun Zhang
,
Yingqi Zhu
,
Yubo Zheng
,
Yingying Luo
,
Hengyi Shao
,
Shaoting Guo
,
Liang Dong
,
Lin Zhang
* and
Lei Li
*
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2024, 14(2), 875; https://doi.org/10.3390/app14020875
Submission received: 27 November 2023 / Revised: 14 January 2024 / Accepted: 17 January 2024 / Published: 19 January 2024
(This article belongs to the Special Issue Modern Advances in Neurolinguistics and EEG Language Processing)
Browse Figures
Review Reports Versions Notes

Abstract

(1) Background: Information overload challenges decision-making in the Industry 4.0 era. While Natural Language Processing (NLP), especially Automatic Text Summarization (ATS), offers solutions, issues with factual accuracy persist. This research bridges cognitive neuroscience and NLP, aiming to improve model interpretability. (2) Methods: This research examined four fact extraction techniques: dependency relation, named entity recognition, part-of-speech tagging, and TF-IDF, in order to explore their correlation with human EEG signals. Representational Similarity Analysis (RSA) was applied to gauge the relationship between language models and brain activity. (3) Results: Named entity recognition showed the highest sensitivity to EEG signals, marking the most significant differentiation between factual and non-factual words with a score of −0.99. The dependency relation followed with −0.90, while part-of-speech tagging and TF-IDF resulted in 0.07 and −0.52, respectively. Deep language models such as GloVe, BERT, and GPT-2 exhibited noticeable influences on RSA scores, highlighting the nuanced interplay between brain activity and these models. (4) Conclusions: Our findings emphasize the crucial role of named entity recognition and dependency relations in fact extraction and demonstrate the independent effects of different models and TOIs on RSA scores. These insights aim to refine algorithms to reflect human text processing better, thereby enhancing ATS models’ factual integrity.
Keywords: natural language processing (NLP); abstractive summarization (ABS); factual extraction; electroencephalography (EEG); representational similarity analysis (RSA) natural language processing (NLP); abstractive summarization (ABS); factual extraction; electroencephalography (EEG); representational similarity analysis (RSA)

Share and Cite

MDPI and ACS Style

Zhang, Z.; Zhu, Y.; Zheng, Y.; Luo, Y.; Shao, H.; Guo, S.; Dong, L.; Zhang, L.; Li, L. Exploring the Cognitive Neural Basis of Factuality in Abstractive Text Summarization Models: Interpretable Insights from EEG Signals. Appl. Sci. 2024, 14, 875. https://doi.org/10.3390/app14020875

AMA Style

Zhang Z, Zhu Y, Zheng Y, Luo Y, Shao H, Guo S, Dong L, Zhang L, Li L. Exploring the Cognitive Neural Basis of Factuality in Abstractive Text Summarization Models: Interpretable Insights from EEG Signals. Applied Sciences. 2024; 14(2):875. https://doi.org/10.3390/app14020875

Chicago/Turabian Style

Zhang, Zhejun, Yingqi Zhu, Yubo Zheng, Yingying Luo, Hengyi Shao, Shaoting Guo, Liang Dong, Lin Zhang, and Lei Li. 2024. "Exploring the Cognitive Neural Basis of Factuality in Abstractive Text Summarization Models: Interpretable Insights from EEG Signals" Applied Sciences 14, no. 2: 875. https://doi.org/10.3390/app14020875

APA Style

Zhang, Z., Zhu, Y., Zheng, Y., Luo, Y., Shao, H., Guo, S., Dong, L., Zhang, L., & Li, L. (2024). Exploring the Cognitive Neural Basis of Factuality in Abstractive Text Summarization Models: Interpretable Insights from EEG Signals. Applied Sciences, 14(2), 875. https://doi.org/10.3390/app14020875

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop