Contributors:
Reading list
survey/review/perspective paper book/book chapter Encyclopedia
Required - Explainable Artificial Intelligence (XAI)
- The Nature of Explanation, Cambridge University Press (1943)
- Explanation in artificial intelligence: Insights from the social sciences, Artificial Intelligence 2019
- Performance vs. competence in human-machine comparisons, PNAS 2020
- A tale of two explanations: Enhancing human trust by explaining robot behavior, Science Robotics 2019
- CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models, iScience 2022
- In situ bidirectional human-robot value alignment, Science Robotics 2022
Required - Pragmatics and Discourse
- Predicting Pragmatic Reasoning in Language Games, Science 2012
- Pragmatics and Discourse, Speech, language, and communication (1995)
- The Rational Speech Act Framework, Annual Review of Linguistics 2023
- One and Done? Optimal Decisions From Very Few Samples, Cognitive Science 2014
- Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding, TACL 2017
Required - Communication
- Visual resemblance and interaction history jointly constrain pictorial meaning, Nature Communications 2023
Optional - Communication
- From communication to language-a psychological perspective, Cognition 1974
- Twelve-month-olds communicate helpfully and appropriately for knowledgeable and ignorant partners, Cognition 2008
- Communication about absent entities in great apes and human infants, Cognition 2015
- Common Ground and Development, Child Development Perspectives
- Revisiting the Evaluation of Theory of Mind through Question Answering, EMNLP 2019
- The interaction engine: cuteness selection and the evolution of the interactional base for language, Philos. Trans. R. Soc. B 2022
- Emergent Graphical Conventions in a Visual Communication Game, NeurIPS 2022
- Animal Communication in Linguistic and Cognitive Perspective, Annual Review of Linguistics 2023
- Social Learning in Animals: The Roots of Culture, Academic Press (1996)
Optional - Pedagogy
- Natural pedagogy, TiCS 2009
- Natural pedagogy as evolutionary adaptation, Philos. Trans. R. Soc. B 2011
- Preschoolers use pedagogical cues to guide radical reorganization of category knowledge, Cognition 2014
- The effects of information utility and teachers’ knowledge on evaluations of under-informative pedagogy across development, Cognition 2022
Optional - Pragmatics
- Learning in the Rational Speech Acts Model, arXiv preprint arXiv:1510.06807
- Pragmatic reasoning through semantic inference, Semantics & Pragmatics 2016
- Word Meaning in Minds and Machines, PsychReview 2021
- Meaning in Language: An Introduction to Semantics and Pragmatics, Oxford Handbook in Linguistics (2010)
Optional - Implicature, Metaphpor, and Humor
- Implicature
- Formalizing the Pragmatics of Metaphor Understanding, CogSci 2014
- The Funny Thing About Incongruity: A Computational Model of Humor in Puns, CogSci 2013
Optional - Rational Speech Act
- Knowledge and Implicature: Modeling Language Understanding as Social Cognition, TopiCS 2013
- Pragmatic Language Interpretation as Probabilistic Inference, TiCS 2016
Optional - Explainable Artificial Intelligence (XAI)
- Interpretable CNNs for Object Classification, PAMI 2021
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, Information Fusion 2020
- The Emerging Landscape of Explainable Automated Planning & Decision Making, IJCAI 2020
- Explanation Perspectives from the Cognitive Sciences-A Survey, IJCAI 2020
Essay
In this lecture, we discussed XAI as a communication process. Given the materials in the lecture and the reading list, discuss
- The major challenges to be resolved in future XAI research;
- Possible ways to resolve these challenges. You can start by identifying essential components in the communicative XAI framework and analyze the limitation beared by every components. Be bold when proposing possible solutions but try to be specific. Your tentative approaches will be more convincing if you include appropriate settings to verify your thoughts.