Research Projects

programming-by-example interface for non-programmers

Igarashi CREST, The University of Tokyo (April 2018 - August 2019)

Programming-by-example (PBE), can be a powerful tool to reduce manual work in repetitive data transformation tasks. However, few examples often leave ambiguity and may cause undesirable data transformation by the system. This ambiguity can be resolved by allowing the user to directly edit the synthesized programs; however, this is difficult for non-programmers. Here, we present a novel approach: data-centric disambiguation for data transformation, where users resolve the ambiguity in data transformation by examining and modifying the output rather than the program. The key idea is to focus on the given set of data the user wants to transform instead of pursuing the synthesized program’s generality or completeness. Our system provides visualization and interaction methods that allow users to efficiently examine and fix the transformed outputs, which is much simpler than understanding and modifying the program itself. The user study suggests that our system can successfully help non-programmers to more easily and efficiently process data.

Data-centric interaction for data transformation with Programming-by-Example

Minori Narita, Nolwenn Maudet, Yi Lu, and Takeo Igarashi. Intelligent User Interfaces (IUI 2021) (acceptance rate=25.0%). 04.2021. [Honorable Mention]

[ACM] [PDF] [video]

FlashAttention: Data-centric Interaction for Data Transformation Using Programming-by-Example

Minori Narita, Nolwenn Maudet, Yi Lu, and Takeo Igarashi. The ACM Symposium on User Interface Software and Technology (UIST 2020), Poster (acceptance ratio=58.9%). 10.2020.

[ACM] [PDF] [poster]

Programming-by-Example for Data Transformation to Improve Machine Learning Performance

Minori Narita and Takeo Igarashi. Intelligent User Interfaces (IUI 2019), Poster. 03.2019.

[ACM] [PDF] [poster]

Other projects are coming soon!