Content Determination for Natural Language Descriptions of Predictive Bayesian Networks

@inproceedings{PereiraFaria2019ContentDF,
  title={Content Determination for Natural Language Descriptions of Predictive Bayesian Networks},
  author={M. Pereira-Fari{\~n}a and Alberto Bugar{\'i}n},
  booktitle={EUSFLAT Conf.},
  year={2019}
}
The dramatic success of Artificial Intelligence and its applications has been accompanied by an increasing complexity, which makes its comprehension for final users more difficult and damages their trustworthiness. Within this context, the emergence of Explainable AI aims to make intelligent systems decisions more transparent and understandable for human users. In this paper, we propose a framework for the explanation of predictive inference in Bayesian Networks (BN) in natural language to non… Expand
Explaining Bayesian Networks in Natural Language: State of the Art and Challenges
TLDR
The importance of a natural language approach to explanation is highlighted and several challenges that remain to be addressed in the generation and validation of natural language explanations of Bayesian Networks are outlined. Expand
Interactive Natural Language Technology for Explainable Artificial Intelligence
TLDR
An interdisciplinary program for training a new generation of researchers who will be ready to leverage the use of Artificial Intelligence (AI)-based models and techniques even by nonexpert users to make AI self-explaining and thus contribute to translating knowledge into products and services for economic and social benefit. Expand

References

SHOWING 1-10 OF 22 REFERENCES
The probabilistic approach to human reasoning
TLDR
The probabilistic approach to logical reasoning is contrasted with other approaches to explaining rationality, and it is shown how it has been applied to three main areas of logical reasoning: conditional inference, Wason's selection task and syllogistic reasoning. Expand
Dynamic Reasoning with Qualified Syllogisms
TLDR
This paper introduces a formal logic Q of such syllogisms and shows how this may be employed in a system of nonmonotonic reasoning, and outlines how the DRS framework accommodates other reasoning techniques—in particular, predicate circumscription, a “localized” version of default logic, a variant of non monotonic logic, and reason maintenance. Expand
A cognitive model of argumentation
In order to argue effectively one must have a grasp of both the normative strength of the inferences that come into play and the effect that the proposed inferences will have on the audience. In thisExpand
Bayesian Informal Logic and Fallacy
  • K. Korb
  • Sociology, Computer Science
  • 2004
TLDR
Bayesian principles provide a framework for understanding ordinary arguments which is well worth developing and are applied informally to more common forms of inference, namely natural language arguments. Expand
A fuzzy syllogistic reasoning schema for generalized quantifiers
TLDR
A new approximate syllogistic reasoning schema is described that expands some of the approaches expounded in the literature into two ways: a number of different types of quantifiers taken from Theory of Generalized Quantifiers and similarity quantifiers are considered and any number of premises can be taken into account within the reasoning process. Expand
Bayesian Artificial Intelligence
TLDR
This book would have been more useful had some more detailed discussion on the choices of ranked set size k and cycle number m been added, however, overall I would highly recommend this well-written and reasonably priced book to researchers and practitioners. Expand
On ‘syllogistic inference’
TLDR
It is hard to see how Johnson-Laird and Bara can believe that the premisses “All A are B” and “ no B are C” “yield validly” the conclusion “Some C are not A,” unless they suppose that “No B areC” implies the non-emptiness of C, i.e., that there are some things to which C applies. Expand
Real versus Template-Based Natural Language Generation: A False Opposition?
This article challenges the received wisdom that template-based approaches to the generation of language are necessarily inferior to other approaches as regards their maintainability, linguistic we...
Building Natural-Language Generation Systems
  • Ehud Reiter
  • Computer Science
  • Computational Linguistics
  • 2001
TLDR
The architecture of a Natural Language Generation system and its implications for national language generation in practice are described. Expand
IJCAI-18 Workshop on Explainable AI (XAI)
  • http://home.earthlink.net/ ̃dwaha/ research/meetings/faim18-xai, last accessed May 15, 2019.
  • 2018
...
1
2
3
...