Alex Haig
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alex Haig has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chih-Wei Hsu
Google Inc, Mountain View, United States
1 shared publication - Christina Göpfert
Amazon.com Inc, Berlin, Germany and Bielefeld University, Bielefeld, Germany
1 shared publication - Craig Boutilier
Google research
1 shared publication - Deepak Ramachandran
Google Inc, Mountain View, United States
1 shared publication - Hubert Pham
Google Research, Mountain View, CA, USA
1 shared publication - Ivan Vendrov
Google Inc, Mountain View, United States and Anthropic, San Francisco, United States
1 shared publication
Latest Publications
- Open Access
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 2 (4) , 1-37
Discovering Personalized Semantics for Soft Attributes in Recommender Systems Using Concept Activation Vectors
Interactive recommender systems have emerged as a promising paradigm to overcome the limitations of the primitive user feedback used by traditional recommender systems (e.g., clicks, item consumption, ratings). They allow users to express intent, preferences, constraints, and contexts in a richer fashion, often using natural language (including faceted search and dialogue). Yet more research is needed to find the most effective ways to use this feedback. One challenge is inferring a user’s semantic intent from the open-ended terms or attributes often used to describe a desired item. This is critical for recommender systems that wish to support users in their everyday, intuitive use of natural language to refine recommendation results. Leveraging concept activation vectors (CAVs) [ 26 ], a recently developed approach for model interpretability in machine learning, we develop a framework to learn a representation that captures the semantics of such attributes and connects them to user preferences and behaviors in recommender systems. One novel feature of our approach is its ability to distinguish objective and subjective attributes (both subjectivity of degree and of sense ) and associate different senses of subjective attributes with different users. We demonstrate on both synthetic and real-world datasets that our CAV representation not only accurately interprets users’ subjective semantics but also can be used to improve recommendations through interactive item critiquing .
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 2 (4) , 1-37
Open AccessDiscovering Personalized Semantics for Soft Attributes in Recommender Systems Using Concept Activation Vectors
Interactive recommender systems have emerged as a promising paradigm to overcome the limitations of the primitive user feedback used by traditional recommender systems (e.g., clicks, item consumption, ratings). They allow users to express intent, preferences, constraints, and contexts in a richer fashion, often using natural language (including faceted search and dialogue). Yet more research is needed to find the most effective ways to use this feedback. One challenge is inferring a user’s semantic intent from the open-ended terms or attributes often used to describe a desired item. This is critical for recommender systems that wish to support users in their everyday, intuitive use of natural language to refine recommendation results. Leveraging concept activation vectors (CAVs) [ 26 ], a recently developed approach for model interpretability in machine learning, we develop a framework to learn a representation that captures the semantics of such attributes and connects them to user preferences and behaviors in recommender systems. One novel feature of our approach is its ability to distinguish objective and subjective attributes (both subjectivity of degree and of sense ) and associate different senses of subjective attributes with different users. We demonstrate on both synthetic and real-world datasets that our CAV representation not only accurately interprets users’ subjective semantics but also can be used to improve recommendations through interactive item critiquing .