APLAS 2022
Mon 5 - Sat 10 December 2022 Auckland, New Zealand
co-located with SPLASH 2022
Mon 5 Dec 2022 17:00 - 17:30 at Seminar Room G007 - Types Chair(s): Atsushi Igarashi

Strong static type systems help programmers eliminate many errors without much burden of supplying type annotations. However, this flexibility makes it highly non-trivial to diagnose ill-typed programs, especially for novice programmers. Compared to classic constraint solving and optimization-based approaches, the data-driven approach has shown great promise in identifying the root causes of type errors with higher accuracy. Instead of relying on hand-engineered features, this work explores natural language models for type error localization, which can be trained in an end-to-end fashion without requiring any features. We demonstrate that, for novice type error diagnosis, the language model-based approach significantly outperforms the previous state-of-the-art data-driven approach. Specifically, our model could predict type errors correctly 62% of the time, outperforming the state-of-the-art Nate’s data-driven model by 11%, in a more rigorous metric of accuracy measurement. Furthermore, we also apply structural probes to explain the performance difference of different language models.

Mon 5 Dec

Displayed time zone: Auckland, Wellington change

15:30 - 17:30
TypesAPLAS at Seminar Room G007
Chair(s): Atsushi Igarashi Kyoto University
15:30
30m
Talk
Characterizing functions mappable over GADTs
APLAS
Patricia Johann Appalachian State University, Pierre Cagne Appalachian State University
16:00
30m
Talk
Applicative Intersection Types
APLAS
Xu Xue University of Hong Kong, Bruno C. d. S. Oliveira University of Hong Kong, Ningning Xie University of Toronto
16:30
30m
Talk
A Calculus with Recursive Types, Record Concatenation and Subtyping
APLAS
Yaoda Zhou University of Hong Kong, Bruno C. d. S. Oliveira University of Hong Kong, Andong Fan Hong Kong University of Science and Technology
17:00
30m
Talk
Novice Type Error Diagnosis with Natural Language Models
APLAS
Chuqin Geng McGill University, Haolin Ye McGill University, Yixuan Li McGill University, Tianyu Han McGill University, Brigitte Pientka McGill University, Xujie Si McGill University, Canada