In order for us to trust artificial intelligence systems, they need to be able to explain their decisions. This article investigates a case-based reasoning (CBR) approach for generating explanations where a new event is explained by combining and modifying explanations of multiple previous events. This approach is implemented in a CBR system for incident analysis where the goal is to identify causes of transportation incidents. The system generates explanations that connect the observed events to the root causes of the incident through intermediate states and events. Explanations for past incidents are automatically extracted from textual incident reports using natural language processing, thus avoiding the manual effort of constructing explanations. The system is evaluated on incident reports from the Transportation Safety Board of Canada, supporting the hypothesis that adapting explanations of multiple previous events rather than a single event results in a more comprehensive explanation of a new event.
A.Aamodt, A knowledge-intensive, integrated approach to problem solving and sustained learning, Knowledge Engineering and Image Processing Group, University of Trondheim, 1991, pp. 27–85.
2.
A.Aamodt, Knowledge-intensive case-based reasoning in CREEK, in: Advances in Case-Based Reasoning, Springer, 2004, pp. 1–15.
3.
M.A.Abedin, V.Ng and L.Khan, Cause identification from aviation safety incident reports via weakly supervised semantic lexicon construction, Journal of Artificial Intelligence Research38(1) (2010), 569–631.
4.
I.Adeyanju, N.Wiratunga, J.A.Recio-García and R.Lothian, Learning to author text with textual CBR, in: ECAI, 2010, pp. 777–782.
I.Androutsopoulos and P.Malakasiotis, A survey of paraphrasing and textual entailment methods, Journal of Artificial Intelligence Research38 (2010), 135–187.
7.
N.Arshadi and K.Badie, A compositional approach to solution adaptation in case-based reasoning and its application to tutoring library, in: Proceedings of 8th German Workshop on Case-Based Reasoning, Lammerbuckel, 2000.
8.
J.Berant, V.Srikumar, P.-C.Chen, A.V.Linden, B.Harding, B.Huang, P.Clark and C.D.Manning, Modeling biological processes for reading comprehension, in: Proceedings of EMNLP, 2014.
9.
R.Bergmann, G.Pews and W.Wilke, Explanation-Based Similarity: A Unifying Approach for Integrating Domain Knowledge Into Case-Based Reasoning for Diagnosis and Planning Tasks, Springer, 1994.
10.
D.Bridge, P.Gomes and N.Seco, Analysing air incident reports: Workshop challenge, in: Proc. of the 4th Workshop on Textual Case-Based Reasoning, 2007.
11.
S.Bromberger, An approach to explanation, Analytical Philosophy2 (1965), 72–105.
12.
S.Brüninghaus and K.D.Ashley, Combining case-based and model-based reasoning for predicting the outcome of legal cases, in: Case-Based Reasoning Research and Development, Springer, 2003, pp. 65–79.
13.
J.G.Carbonell, Derivational analogy: A theory of reconstructive problem solving and expertise acquisition, in: Machine Learning: An Artificial Intelligence Approach, R.Michalski, J.Carbonell and T.Mitchell, eds, Morgan Kaufman, San Mateo, CA, 1986, pp. 371–392.
14.
W.J.Clancey, The epistemology of a rule-based expert system – A framework for explanation, Artificial Intelligence20(3) (1983), 215–251. doi:10.1016/0004-3702(83)90008-5.
15.
M.T.Cox and A.Ram, Introspective multistrategy learning: On the construction of learning strategies, Artificial Intelligence112(1–2) (1999), 1–55. doi:10.1016/S0004-3702(99)00047-8.
16.
P.Cunningham, D.Doyle and J.Loughrey, An evaluation of the usefulness of case-based explanation, in: Case-Based Reasoning Research and Development, Springer, 2003, pp. 122–130.
17.
V.Dufour-Lussier, F.Le Ber, J.Lieber and E.Nauer, Automatic case acquisition from texts for process-oriented case-based reasoning, Information Systems40 (2014), 153–167. doi:10.1016/j.is.2012.11.014.
18.
K.M.Gupta and D.W.Aha, Conversation for textual case-based reasoning, in: Proc. of the 4th Workshop on Textual Case-Based Reasoning, 2007.
19.
G.H.Harman, The inference to the best explanation, The Philosophical Review74 (1965), 88–95.
20.
C.G.Hempel, Aspects of Scientific Explanation, 1965.
21.
C.G.Hempel and P.Oppenheim, Studies in the logic of explanation, Philosophy of Science15 (1948), 135–175.
22.
F.Hogenboom, F.Frasincar, U.Kaymak and F.De Jong, An overview of event extraction from text, in: Workshop on Detection, Representation, and Exploitation of Events in the Semantic Web at ISWC 2011, Vol. 779, 2011, pp. 48–57, Citeseer.
23.
J.R.Josephson and S.G.Josephson, Abductive Inference: Computation, Philosophy, Technology, Cambridge University Press, 1996.
24.
A.M.Kass and D.B.Leake, Case-based reasoning applied to constructing explanations, in: Proc. of a Workshop on Case-Based Reasoning, Holiday Inn, Clearwater Beach, FL, 1988, pp. 190–208.
25.
C.S.Khoo, J.Kornfilt, R.N.Oddy and S.H.Myaeng, Automatic extraction of cause-effect information from newspaper text without knowledge-based inferencing, Literary and Linguistic Computing13(4) (1998), 177–186. doi:10.1093/llc/13.4.177.
26.
H.W.Kuhn, The Hungarian method for the assignment problem, Naval Research Logistics Quarterly2(1–2) (1955), 83–97. doi:10.1002/nav.3800020109.
27.
A.Kumar, O.Irsoy, J.Su, J.Bradbury, R.English, B.Pierce, P.Ondruska, I.Gulrajani and R.Socher, Ask me anything: Dynamic memory networks for natural language processing, CoRR, 2015.
28.
C.Leacock, G.A.Miller and M.Chodorow, Using corpus statistics and WordNet relations for sense identification, Computational Linguistics24(1) (1998), 147–165.
29.
D.B.Leake, Evaluating Explanations: A Content Theory, L. Erlbaum Associates, Hillsdale, NJ, 1992.
30.
D.B.Leake, L.Birnbaum, K.Hammond, C.Marlow and H.Yang, An integrated interface for proactive, experience-based design support, in: Proceedings of the 6th International Conference on Intelligent User Interfaces, ACM, 2001, pp. 101–108.
31.
C.D.Manning, M.Surdeanu, J.Bauer, J.Finkel, S.J.Bethard and D.McClosky, The Stanford CoreNLP natural language processing toolkit, in: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2014, pp. 55–60.
32.
S.Massie, S.Craw and N.Wiratunga, Visualisation of case-base reasoning for explanation, in: Proceedings of the ECCBR 2004 Workshops, Madrid, 2004, pp. 135–144, Citeseer.
33.
S.Massie, N.Wiratunga, S.Craw, A.Donati and E.Vicari, From anomaly reports to cases, in: Case-Based Reasoning Research and Development, Springer, 2007, pp. 359–373.
34.
G.P.McArdle and D.C.Wilson, Visualising case-base usage, in: Workshop Proceedings ICCBR, 2003, pp. 105–114.
T.Mikolov, I.Sutskever, K.Chen, G.S.Corrado and J.Dean, Distributed representations of words and phrases and their compositionality, in: Advances in Neural Information Processing Systems, 2013, pp. 3111–3119.
37.
G.A.Miller, WordNet: A lexical database for English, Communications of the ACM38(11) (1995), 39–41. doi:10.1145/219717.219748.
38.
A.Orecchioni, N.Wiratunga, S.Massie, S.Chakraborti and R.Mukras, Learning incident causes, in: Proc. of the 4th Workshop on Textual Case-Based Reasoning, 2007.
39.
C.S.Peirce, Pragmatism as the logic of abduction [1903], in: The Essential Peirce, Vol. 21998, pp. 226–241.
40.
E.Plaza, E.Armengol and S.Ontañón, The explanatory power of symbolic similarity in case-based reasoning, Artificial Intelligence Review24(2) (2005), 145–161. doi:10.1007/s10462-005-4608-6.
41.
C.Posse, B.Matzke, C.Anderson, A.Brothers, M.Matzke and T.Ferryman, Extracting information from narratives: An application to aviation safety reports, in: Aerospace Conference, 2005 IEEE, IEEE, 2005, pp. 3678–3690.
42.
J.A.Recio-García, B.Díaz-Agudo and P.A.González-Calero, Textual CBR in jCOLIBRI: From retrieval to reuse, in: Proceedings of the ICCBR 2007 Workshop on Textual Case-Based Reasoning: Beyond Retrieval, 2007, pp. 217–226, Citeseer.
43.
R.C.Schank, Explanation: A first pass, in: Experience, Memory, and Reasoning, 1986, pp. 139–165.
44.
R.C.Schank and A.Kass, Inside Case-Based Explanation, Psychology Press, 1994.
45.
R.C.Schank and D.B.Leake, Creativity and learning in a case-based explainer, Artificial Intelligence40(1) (1989), 353–385. doi:10.1016/0004-3702(89)90053-2.
46.
G.Sizov, P.Öztürk and A.Aamodt, Evidence-driven retrieval in textual CBR: Bridging the gap between retrieval and reuse, in: Case-Based Reasoning Research and Development, Springer, 2015, pp. 351–365.
47.
G.Sizov, P.Öztürk and E.Marsi, Compositional adaptation of explanations in textual case-based reasoning, in: Case-Based Reasoning Research and Development, Springer, 2016, pp. 387–401.
48.
G.Sizov, P.Öztürk and J.Štyrák, Acquisition and reuse of reasoning knowledge from textual cases for automated analysis, in: Case-Based Reasoning Research and Development, Springer, 2014, pp. 465–479.
49.
S.Tirunagari, M.Hanninen, K.Stanhlberg and P.Kujala, Mining causal relations and concepts in maritime accidents investigation reports, International Journal of Innovative Research and Development1(10) (2012), 548–566.
50.
F.Toolan, J.Carthy, A.Drummond and J.Dunnion, Automating incident analysis: A challenge paper, in: 2nd Workshop on the Investigation and Reporting of Incidents and Accidents, Williamsburg, Virginia, United States, 2003, pp. 99–109.
51.
C.Tsatsoulis and H.A.Amthauer, Finding clusters of similar events within clinical incident reports: A novel methodology combining case based reasoning and information retrieval, Quality and Safety in Health Care12(suppl. 2) (2003), ii24–ii32.
52.
D.C.Wilson, J.Carthy, K.Abbey, J.Sheppard, J.Dunnion, A.Drummondet al., Textual CBR for incident report retrieval, in: Computational Science and Its Applications – ICCSA 2003, Springer, 2003, pp. 358–367.
53.
X.Zhang and Y.LeCun, Text understanding from scratch, arXiv preprint, arXiv:1502.01710, 2015.
