Abstract
State-of-the-art (SOTA) transformer-based models in the domains of Natural Language Processing (NLP) and Information Retrieval (IR) are often characterized by their opacity in terms of decision-making processes. This limitation has given rise to various techniques for enhancing model interpretability and the emergence of evaluation benchmarks aimed at designing more transparent models. These techniques are primarily focused on developing interpretable models with the explicit aim of shedding light on the rationales behind their predictions. Concurrently, evaluation benchmarks seek to assess the quality of these rationales provided by the models. Despite the availability of numerous resources for using these techniques and benchmarks independently, their seamless integration remains a non-trivial task. In response to this challenge, this work introduces an end-to-end toolkit that integrates the most common techniques and evaluation approaches for interpretability. Our toolkit offers user-friendly resources facilitating fast and robust evaluations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bahdanau, D., Cho, K.H., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015 (2015)
Bhattarai, B., Granmo, O.C., Jiao, L.: An interpretable knowledge representation framework for natural language processing with cross-domain application. In: Kamps, J., et al. (eds.) ECIR 2023. LNCS, vol. 13980, pp. 167–181. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-28244-7_11
Danilevsky, M., Qian, K., Aharonov, R., Katsis, Y., Kawas, B., Sen, P.: A survey of the state of explainable AI for natural language processing. In: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pp. 447–459 (2020)
DeYoung, J., et al.: ERASER: a benchmark to evaluate rationalized NLP models. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4443–4458. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.acl-main.408
Dwivedi, R., et al.: Explainable AI (XAI): core ideas, techniques, and solutions. ACM Comput. Surv. 55(9), 1–33 (2023)
Hayati, S.A., Kang, D., Ungar, L.: Does BERT learn as humans perceive? Understanding linguistic styles through lexica. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6323–6331. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021). https://doi.org/10.18653/v1/2021.emnlp-main.510
Karlekar, S., Niu, T., Bansal, M.: Detecting linguistic characteristics of Alzheimer’ dementia by interpreting neural models. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 701–707 (2018)
Lyu, L., Anand, A.: Listwise explanations for ranking models using multiple explainers. In: Kamps, J., et al. (eds.) ECIR 2023. LNCS, vol. 13980, pp. 653–668. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-28244-7_41
Mathew, B., Saha, P., Yimam, S.M., Biemann, C., Goyal, P., Mukherjee, A.: Hatexplain: a benchmark dataset for explainable hate speech detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 17, pp. 14867–14875 (2021). https://doi.org/10.1609/aaai.v35i17.17745
Narang, S., Raffel, C., Lee, K., Roberts, A., Fiedel, N., Malkan, K.: Wt5?! training text-to-text models to explain their predictions. arXiv preprint arXiv:2004.14546 (2020)
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., Huang, X.: Pre-trained models for natural language processing: a survey. SCIENCE CHINA Technol. Sci. 63(10), 1872–1897 (2020)
Ras, G., Xie, N., Van Gerven, M., Doran, D.: Explainable deep learning: a field guide for the uninitiated. J. Artif. Intell. Res. 73, 329–396 (2022)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?”: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016, pp. 1135–1144 (2016)
Ross, A., Marasović, A., Peters, M.E.: Explaining NLP models via minimal contrastive editing (MICE). In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 3840–3852 (2021)
Sundararajan, M., Najmi, A.: The many shapley values for model explanation. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020. JMLR.org (2020)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wiegreffe, S., Marasovic, A.: Teach me to explain: a review of datasets for explainable natural language processing. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1) (2021)
Yates, A., Nogueira, R., Lin, J.: Pretrained transformers for text ranking: BERT and beyond. In: Kondrak, G., Bontcheva, K., Gillick, D. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials, pp. 1–4. Association for Computational Linguistics, Online (2021). https://doi.org/10.18653/v1/2021.naacl-tutorials.1
Acknowledgments
The authors would thank the support of the In-Utero project funded by HDH (France) and FRQS (Canada).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Maachou, K., Lovón-Melgarejo, J., Moreno, J.G., Tamine, L. (2024). eval-rationales: An End-to-End Toolkit to Explain and Evaluate Transformers-Based Models. In: Goharian, N., et al. Advances in Information Retrieval. ECIR 2024. Lecture Notes in Computer Science, vol 14612. Springer, Cham. https://doi.org/10.1007/978-3-031-56069-9_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-56069-9_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56068-2
Online ISBN: 978-3-031-56069-9
eBook Packages: Computer ScienceComputer Science (R0)