Geodesic
Automatic evaluation of interpretability methods in text categorization
Zapiski Nauchnykh Seminarov POMI, Investigations on applied mathematics and informatics. Part II–2, Tome 530 (2023), pp. 68-79 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice du chapitre de livre

Neural networks have begun to take over more and more of a person's everyday life, and the complexity of neural networks is only increasing. When tested on collected test data, the model can show quite decent performance, but when used in real-life conditions, it can give completely unexpected results. To determine the cause of the error, it is important to know how the model makes its decisions. In this work, we consider various methods of interpreting the BERT model in classification tasks, and also consider a method for evaluating interpretation methods using vector representations fastText and GloVe. 
@article{ZNSL_2023_530_a5,
     author = {A. Rogov and N. Lukashevich},
     title = {Automatic evaluation of interpretability methods in text categorization},
     journal = {Zapiski Nauchnykh Seminarov POMI},
     pages = {68--79},
     year = {2023},
     volume = {530},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/ZNSL_2023_530_a5/}
}
TY  - JOUR
AU  - A. Rogov
AU  - N. Lukashevich
TI  - Automatic evaluation of interpretability methods in text categorization
JO  - Zapiski Nauchnykh Seminarov POMI
PY  - 2023
SP  - 68
EP  - 79
VL  - 530
UR  - http://geodesic.mathdoc.fr/item/ZNSL_2023_530_a5/
LA  - en
ID  - ZNSL_2023_530_a5
ER  - 
%0 Journal Article
%A A. Rogov
%A N. Lukashevich
%T Automatic evaluation of interpretability methods in text categorization
%J Zapiski Nauchnykh Seminarov POMI
%D 2023
%P 68-79
%V 530
%U http://geodesic.mathdoc.fr/item/ZNSL_2023_530_a5/
%G en
%F ZNSL_2023_530_a5
A. Rogov; N. Lukashevich. Automatic evaluation of interpretability methods in text categorization. Zapiski Nauchnykh Seminarov POMI, Investigations on applied mathematics and informatics. Part II–2, Tome 530 (2023), pp. 68-79. http://geodesic.mathdoc.fr/item/ZNSL_2023_530_a5/

[1] 20 newsgroups dataset, http://people.csail.mit.edu/jrennie/20Newsgroups/

[2] J. Devlin, M. Chang, K. Lee, and K. Toutanova, BERT: pre-training of deep bidirectional transformers for language understanding, 2018, arXiv: 1810.04805

[3] F. Doshi-Velez and B. Kim, “Towards a rigorous science of interpretable machine learning”, Stat., 1050 (2017), 2 | MR

[4] E. Doumard, J. Aligon, E. Escriva, J.-B. Excoffier, P. Monsarrat, and C. Soulé-Dupuy, “A quantitative approach for the comparison of additive local explanation methods”, Information Systems, 114 (2023), 102162 | DOI

[5] Facebook AI, fastText: Library for fast text representation and classification, 2016

[6] A. Garcia-Silva and J. M. Gomez-Perez, Classifying scientific publications with BERT: Is self-attention a feature selection method?, Advances in Information Retrieval, 43rd European Conference on IR Research, ECIR 2021, Proceedings (Virtual Event, March 28–April 1, 2021), v. I, Springer, 2021, 161–175

[7] K. Järvelin and J. Kekäläinen, “Cumulated gain-based evaluation of IR techniques”, ACM Transactions on Information Systems (TOIS), 20:4 (2002), 422–446 | DOI

[8] K. Kowsari, D. E. Brown, M. Heidarysafa, K. Jafari Meimandi, M. S. Gerber, and L. E. Barnes, “Hdltex: Hierarchical deep learning for text classification”, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, 2017

[9] P. Lertvittayakumjorn and F. Toni, “Human-grounded evaluations of explanation methods for text classification”, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, 5195–5205

[10] X. Li, H. Xiong, X. Li, X. Wu, X. Zhang, J. Liu, J. Bian, and D. Dou, “Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond”, Knowledge and Information Systems, 64:12 (2022), 3197–3234 | DOI

[11] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions”, Advances in neural information processing systems, 30 (2017)

[12] A. Madsen, S. Reddy, and S. Chandar, “Post-hoc interpretability for neural NLP: A survey”, ACM Computing Surveys, 55:8 (2022), 1–42 | DOI

[13] J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global vectors for word representation”, Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014, 1532–1543 | DOI

[14] M. T. Ribeiro, S. Singh, and C. Guestrin, “"Why should i trust you?" Explaining the predictions of any classifier”, Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, 1135–1144 | DOI

[15] M. O. Yalcin and X. Fan, On evaluating correctness of explainable ai algorithms: an empirical study on local explanations for classification, 2021