Abstract
Recent advances in artificial intelligence raise a number of concerns. Among the challenges to be addressed by researchers, accountability of artificial intelligence solutions is one of the most critical. This paper focuses on artificial intelligence applications using natural language to investigate if the core semantics defined for a large-scale natural language processing system could assist in addressing accountability issues. Core semantics aims to obtain a full interpretation of the content of natural language texts, representing both implicit and explicit knowledge, using only ‘subj-action-(obj)’ structures and causal, temporal, spatial and personal-world links. The first part of the paper offers a summary of the difficulties to be addressed and of the reasons why representing the meaning of a natural language text is relevant for artificial intelligence accountability. In the second part, a-proof-of-concept for the application of such a knowledge representation to support accountability, and a detailed example of the analysis obtained with a prototype system named CoreSystem is illustrated. While only preliminary, these results give some new insights and indicate that the provided knowledge representation can be used to support accountability, looking inside the box.
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
Notes
- 1.
The following brief description of the prototype system is provided in order to outline what has been used to produce the analysis below. The system is at present not available for external testing; furthermore, as it is under development, no claims are made here to its coverage or efficiency with respect to other NLP systems.
References
LeCun, Y., Yoshua, B., Geoffry, H.: Deep learning. Nature 521(7553), 436 (2015)
Davis, A.: How artificial intelligence has crept into our everyday lives. IEEE Special Report (2016). http://theinstitute.ieee.org/static/special-report-artificial-intelligence
LinkedIn: Global recruiting trends 2018 (2018). https://business.linkedin.com/talent-solutions/recruiting-tips/2018-global-recruiting-trends?trk=bl-ba_global-recruiting-trends-launch_maria-ignatova_011018
Kaplan, J.: Artificial intelligence: think again. Commun. ACM 60(1), 36–38 (2016). https://doi.org/10.1145/2950039
Internet Society: Artificial Intelligence and Machine Learning: Policy paper (2017). https://www.internetsociety.org/resources/doc/2017/artificial-intelligence-and-machine-learning-policy-paper
Parnas, D.L.: The real risks of artificial intelligence. Commun. ACM 60(10), 27–31 (2017). https://doi.org/10.1145/3132724
Shanahan, M.: The Technological Singularity. MIT Press, New York (2015)
Anthes, G.: Artificial intelligence poised to ride a new wave. Commun. ACM 60(7), 19–21 (2017). https://doi.org/10.1145/3088342
Guidotti, R., Monreale, A., Pedreschi, D.: The AI black box explanation problem. ERCIM News 116, 12–13 (2019)
ACM U.S. Public Policy Council, ACM Europe Policy Committee: Statement on algorithmic transparency and accountability (2017). https://www.acm.org/binaries/content/assets/public-policy/2017_joint_statement_algorithms.pdf
Doshi-Velez, F., et al.: Accountability of AI under the law: the role of explanation. CoRR abs/1711.01134 (2017)
O’Neil, C.: Weapons of math destruction: how big data increases inequality and threatens democracy. New York Time (2016)
Pell, D.: The 10 algorithms that rule the world and other fascinating news on the web. Time (2014). http://time.com/111313/the-10-algorithms-that-rule-the-world-and-other-fascinating-news-on-the-web
Barry-Jester, A.M., Casselman, B., Goldestein, D.: The Marshall Project. The new science of sentencing (2015). https://www.themarshallproject.org/2015/08/04/the-new-science-of-sentencing#.bwuhXcwqn
Buregess, M.: Holding AI to account: will algorithms ever be free from bias if they’re created by humans? Wired, UK (2016). http://www.wired.co.uk/article/creating-transparent-ai-algorithms-machine-learning
Kirkpatrick, K.: Battling algorithmic bias: how do we ensure algorithms treat us fairly? Commun. ACM 59(10), 16–17 (2016). https://doi.org/10.1145/2983270
Gaines, B.: Designing expert systems for usability. In: Shackel, B., Richardson, S.J. (eds.) Human Factors for Informatics Usability, pp. 207–246. Cambridge University Press, New York (1991)
Johnson-Laird, P.: How We Reason. Oxford University Press, New York (2006)
Wong, S.: Google Translate AI invents its own language to translate with. Daily News (2016). https://www.newscientist.com/article/2114748-google-translate-ai-invents-its-own-language-to-translate-with
Reynolds, M.: Google uses neural networks to translate without transcribing. Daily News (2017). https://www.newscientist.com/article/2126738-google-uses-neural-networks-to-translate-without-transcribing
Coldewey, D., Lardinois, F.: DeepL schools other online translators with clever machine learning. Techcrunch (2017). https://techcrunch.com/2017/08/29/deepl-schools-other-online-translators-with-clever-machine-learning
Mitchell, M.P., Santorini, B., Marcinkiewicz, M.A., Taylor, A.: Treebank-3 LDC99T42 Web Download. Linguistic Data Consortium, Philadelphia (1999)
Schank, S., Abelson, R.: Scripts, Plans, Goals and Understanding. An Inquiry into Human Knowledge Structures. Lawrence Erlbaum, Hillsdale (1997)
He, L., Lee, K., Lewis, M., Zettlemoyer, L.: Deep semantic role labeling: what works and what’s next. In: Proceedings of the 55th Annual Meeting Association for Computational Linguistics, vol. 1, pp. 473–483 (2017)
Jordan, M.: Artificial Intelligence. The revolution hasn’t happened yet. Medium (2018). https://medium.com/@mijordan3/artificial-intelligence-the-revolution-hasnt-happened-yet-5e1d5812e1e7
Hutson, M.: AI researchers allege that machine learning is alchemy. Science 360(6388), 861 (2018). http://www.sciencemag.org/news/2018/05/ai-researchers-allege-machine-learning-alchemy
Acknowledgments
As researchers in natural language processing and requirements engineering, authors shared a number of papers with Stefania Gnesi and her research group since the early 1990s. She is a passionate scientist, and these exchanges resulted in a fruitful and enriching relationship.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A
Appendix A
Representation of the Meaning of the Sentence: “A 59-year-old man from York has been arrested on suspicion of murdering missing chef Claudia Lawrence”.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Garigliano, R., Mich, L. (2019). Looking Inside the Black Box: Core Semantics Towards Accountability of Artificial Intelligence. In: ter Beek, M., Fantechi, A., Semini, L. (eds) From Software Engineering to Formal Methods and Tools, and Back. Lecture Notes in Computer Science(), vol 11865. Springer, Cham. https://doi.org/10.1007/978-3-030-30985-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-30985-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30984-8
Online ISBN: 978-3-030-30985-5
eBook Packages: Computer ScienceComputer Science (R0)