Proceedings of the 24th International Conference on Intelligent User Interfaces 2019
DOI: 10.1145/3301275.3302316
|View full text |Cite
|
Sign up to set email alerts
|

Automated rationale generation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

3
43
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
3

Relationship

1
6

Authors

Journals

citations
Cited by 147 publications
(46 citation statements)
references
References 27 publications
3
43
0
Order By: Relevance
“…Finally, work by Ehsan et al (2019) presented a novel approach for generating rationales (the authors note a distinction between this and explanations, indicating that rationales do not need to explain the inner workings of the underlying model). The method involves conducting a modified thinkaloud user study of the target application (in this case, the game Frogger) where participants are prompted to verbally indicate their rationale for each action they take.…”
Section: Human Collaborationmentioning
confidence: 99%
See 1 more Smart Citation
“…Finally, work by Ehsan et al (2019) presented a novel approach for generating rationales (the authors note a distinction between this and explanations, indicating that rationales do not need to explain the inner workings of the underlying model). The method involves conducting a modified thinkaloud user study of the target application (in this case, the game Frogger) where participants are prompted to verbally indicate their rationale for each action they take.…”
Section: Human Collaborationmentioning
confidence: 99%
“…Sixteen of the papers reviewed were either agents within video games or were tested with video game problems, and surprisingly few were on more real-world applications such as autonomous driving or robotics. Examples of this include Ehsan et al (2019) who provide an interesting example but is highly scoped to the Frogger game, and Madumal et al (2020) who looked at Starcraft II. While this is naturally following on from the success of DeepMind, and video game problems provide for challenging RL tasks, there is an opportunity for more work on applications outside of this domain.…”
Section: Use Of Toy Examples Specific Applications and Limited Scalabilitymentioning
confidence: 99%
“…Arent et al [177] present a technique that generalizes parallel coordinated visualization techniques to sequences of learned representations. Eshan et al [178] created a technique to generate rationales automatically. Le et al [179] developed a model to identify fingers in capacitive touchscreens.…”
Section: Algorithmsmentioning
confidence: 99%
“…Features of AI models addressing the concerns of users to improve the usability and adoptability of AI systems such as explainability, interpretability, privacy, and fairness have been the focus of many HCML related work [6,12,20,26,58,73,76,81,104,178,219]. This is not surprising, given the history of XAI research area dates back to 1980s [220,221].…”
Section: Features Of the Modelsmentioning
confidence: 99%
“…Rationale generation is thus the task of creating an explanation comparable to what a human would say if he or she were performing the behavior that the agent was performing in the same situation. Ehsan, Tambwekar, Chan, Harrison, and Riedl () show that human‐like rationales, despite being true reflections of the internal processes of a black‐box intelligent system, promote feelings of trust, rapport, familiarity, and comfort in nonexperts operating autonomous systems and robots.…”
Section: Ai Systems Helping Humans Understand Themmentioning
confidence: 99%