Abstract
This paper demonstrates how case-based reasoning (CBR) can be used for an explainable artificial intelligence (XAI) approach to justify solutions produced by an opaque learning method (i.e., target method), particularly in the context of unstructured textual data. Our general hypothesis is twofold: (1) There exists patterns in the relationship between problems and solutions and there should be data or a body of knowledge that describes how problems and solutions relate; and (2) the identification, manipulation, and learning of such patterns through case features can help create and reuse explanations for solutions produced by the target method. When the target method relies on neural network architectures (e.g., deep learning), the resulting latent space (i.e., word embeddings) becomes useful for finding patterns and semantic relatedness in textual data. In the proposed approach, case problems are input-output pairs from the target method, and case solutions are explanations. We exemplify our approach by explaining recommended citations from Citeomatic - a multi-layer neural-network architecture from the Allen Institute for Artificial Intelligence. Citation analysis is the body of knowledge that describes how query documents (i.e., inputs) relate to recommended citations (i.e., outputs). We build cases and similarity assessment to learn features that represent patterns between problems and solutions that can lead to the reuse of corresponding explanations. The illustrative implementation we present becomes an explanation-augmented citation recommender that targets human-computer trust.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
- 3.
- 4.
PVDM stands for distributed memory model of paragraph vectors as per [21]
- 5.
- 6.
- 7.
- 8.
- 9.
- 10.
References
Sørmo, F., Cassens, J., Aamodt, A.: Explanation in case-based reasoning: perspectives and goals. Artif. Intell. Rev. 24(2), 109–143 (2005)
Nugent, C., Cunningham, P.: A case-based explanation system for black-box systems. Artif. Intell. Rev. 24(2), 163–178 (2005)
Weber, R.O., Ashley, K.D., Brüninghaus, S.: Textual case-based reasoning. Knowl. Eng. Rev. 20(3), 255–260 (2005)
Biran, O., Cotton, C.: Explanation and justification in machine learning: a survey. In: Aha, D.W., Darrell, T., Pazzani, M., Reid, D., Sammut, C., Stone, P. (eds.) Explainable AI: Papers from the IJCAI Workshop, pp. 8–13. Melbourne, Australia (2017)
Li, O., Liu, H., Chen, C., Rudin, C.: Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: AAAI Conference on Artificial Intelligence. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17082/16552. Accessed 15 June 2018
Leake, D.B.: Evaluating explanations: a content theory. Lawrence Erlbaum Associates (1992). Reprint Psychology Press, New York (2014)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Bhagavatula, C., Feldman, S., Power, R., Ammar, W.: Content-based citation recommendation. In: NAACL: HLT (2018). http://aclweb.org/anthology/N18-1022. Accessed 15 June 2018
Xiong, C., Power, R., Callan, J.: Explicit semantic ranking for academic search via knowledge graph embedding. In: Proceedings of the 26th International Conference on World Wide Web, pp. 1271–1279. ACM (2017)
Nanba, H., Okumura, M.: Towards multi-paper summarization using reference information. In: Sixteenth International Joint Conference on Artificial Intelligence, pp. 926–931 (1999)
Qazvinian, V., et al.: Generating extractive summaries of scientific paradigms. J. Artif. Intell. Res. 46, 165–201 (2013)
Tsafnat, G., Dunn, A., Glasziou, P., Coiera, E.: The automation of systematic reviews. BMJ 346, f139 (2013)
Garfield, E.: Citation indexes for science. Science 122, 108–111 (1955)
Small, H.: Co-citation in scientific literature-new measure of relationship between 2 documents. J. Am. Soc. Inf. Sci. 24(4), 265–269 (1973)
Ding, Y., Zhang, G., Chambers, T., Song, M., Wang, X., Zhai, C.: Content-based citation analysis. The next generation of citation analysis. J. Assoc. Inf. Sci. Technol. 65(9), 1820–1833 (2014)
Huang, W., Wu, Z., Chen, L., Mitra, P., Giles, C.L.: A neural probabilistic model for context based citation recommendation. In: AAAI, pp. 2404–2410. AAAI (2015)
Valenzuela, M., Ha, V., Etzioni, O.: Identifying meaningful citations. In: AAAI Workshop: Scholarly Big Data (2015)
Blake, C.: Beyond genes, proteins, and abstracts: Identifying scientific claims from full-text biomedical articles. J. Biomed. Inf. 43(2), 173–189 (2010)
Radev, D.R., Muthukrishnan, P., Qazvinian, V., Abu-Jbara, A.: The ACL anthology network corpus. Lang. Resour. Eval. 47(4), 919–944 (2013)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). https://arxiv.org/abs/1301.3781. Accessed 15 June 2018
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188–1196 (2014)
Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: International Conference on Machine Learning, pp. 957–966 (2015)
Schank, R.C.: Explanation Patterns– Understanding Mechanically and Creatively. Lawrence Erlbaum, New York (1986)
Schank, R.C., Leake, D.: Creativity and learning in a case-based explainer. Artif. Intell. 40(1–3), 353–385 (1989)
Aamodt, A.: Explanation-driven case-based reasoning. In: Wess, S., Althoff, K.-D., Richter, Michael M. (eds.) EWCBR 1993. LNCS, vol. 837, pp. 274–288. Springer, Heidelberg (1994). https://doi.org/10.1007/3-540-58330-0_93
Kofod-Petersen, A., Cassens, J., Aamodt, A.: Explanatory capabilities in the CREEK knowledge-intensive case-based reasoner. Front. Artif. Intell. Appl. 173, 28–35 (2008)
Roth-Berghofer, T.R.: Explanations and case-based reasoning: foundational issues. In: Funk, P., González Calero, P.A. (eds.) ECCBR 2004. LNCS (LNAI), vol. 3155, pp. 389–403. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-28631-8_29
Kindermans, P-J, et al.: The (un)reliability of saliency methods. In: 31st Conference on Neural Information Processing Systems (NIPS) (2017)
Wilson, D.C., Bradshaw, S.: CBR Textuality. Expert. Updat. 3(1), 28–37 (2000)
Wiratunga, N., Koychev, I., Massie, S.: Feature selection and generalisation for retrieval of textual cases. In: Funk, P., González Calero, P.A. (eds.) ECCBR 2004. LNCS (LNAI), vol. 3155, pp. 806–820. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-28631-8_58
Dumais, S.T., Furnas, G.W., Landauer, T.K., Deerwester, S., Harshman, R.: Using latent semantic analysis to improve access to textual information. In: SIGCHI Conference on Human Factors in Computing Systems, pp. 281–285. ACM (1988)
Acknowledgements
We would like to thank the anonymous reviewers who helped improve the quality of this work. We also would like to thank Meaghan Lutts for her help labeling citations.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Weber, R.O., Johs, A.J., Li, J., Huang, K. (2018). Investigating Textual Case-Based XAI. In: Cox, M., Funk, P., Begum, S. (eds) Case-Based Reasoning Research and Development. ICCBR 2018. Lecture Notes in Computer Science(), vol 11156. Springer, Cham. https://doi.org/10.1007/978-3-030-01081-2_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-01081-2_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01080-5
Online ISBN: 978-3-030-01081-2
eBook Packages: Computer ScienceComputer Science (R0)