Textual Explanations and Critiques in Recommendation Systems
It addresses the problem of user understanding and control in AI systems, particularly for recommendation systems and NLP, but appears incremental as it builds on existing interpretability efforts.
The dissertation tackled the lack of interpretability in AI models for decision-critical fields by developing a framework for generating high-quality textual explanations and making them actionable through critiquing, demonstrating that interpretability does not reduce performance in NLP and recommendation tasks.
Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual data. Moreover, with more data available than ever before, it has become increasingly important to explain automated predictions. Generally, users find it difficult to understand the underlying computational processes and interact with the models, especially when the models fail to generate the outcomes or explanations, or both, correctly. This problem highlights the growing need for users to better understand the models' inner workings and gain control over their actions. This dissertation focuses on two fundamental challenges of addressing this need. The first involves explanation generation: inferring high-quality explanations from text documents in a scalable and data-driven manner. The second challenge consists in making explanations actionable, and we refer to it as critiquing. This dissertation examines two important applications in natural language processing and recommendation tasks. Overall, we demonstrate that interpretability does not come at the cost of reduced performance in two consequential applications. Our framework is applicable to other fields as well. This dissertation presents an effective means of closing the gap between promise and practice in artificial intelligence.