Related papers: Inferring Pluggable Types with Machine Learning

Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…

Deep Learning (DL) libraries like TensorFlow and Pytorch simplify machine learning (ML) model development but are prone to bugs due to their complex design. Bug-finding techniques exist, but without precise API specifications, they produce…

Inferring semantic types for entity mentions within text documents is an important asset for many downstream NLP tasks, such as Semantic Role Labelling, Entity Disambiguation, Knowledge Base Question Answering, etc. Prior works have mostly…

When analyzing programs, large libraries pose significant challenges to static points-to analysis. A popular solution is to have a human analyst provide points-to specifications that summarize relevant behaviors of library code, which can…

The Generative Adversarial Network framework has shown success in implicitly modeling data distributions and is able to generate realistic samples. Its architecture is comprised of a generator, which produces fake data that superficially…

The increasing demand for programming language education and growing class sizes require immediate and personalized feedback. However, traditional code review methods have limitations in providing this level of feedback. As the capabilities…

As artificial intelligence (AI) technologies become increasingly powerful and prominent in society, their misuse is a growing concern. In educational settings, AI technologies could be used by students to cheat on assignments and exams. In…

The increasing complexity of deep learning models necessitates specialized hardware and software optimizations, particularly for deep learning accelerators. Existing autotuning methods often suffer from prolonged tuning times due to…

Inductive link prediction is emerging as a key paradigm for real-world knowledge graphs (KGs), where new entities frequently appear and models must generalize to them without retraining. Predicting links in a KG faces the challenge of…

Large language models (LLMs), especially generative pre-trained transformers (GPTs), have recently demonstrated outstanding ability in information comprehension and problem-solving. This has motivated many studies in applying LLMs to…

In principle, the design of transition-based dependency parsers makes it possible to experiment with any general-purpose classifier without other changes to the parsing algorithm. In practice, however, it often takes substantial software…

Inductive datatypes in programming languages allow users to define useful data structures such as natural numbers, lists, trees, and others. In this paper we show how inductive datatypes may be added to the quantum programming language QPL.…

We present a new method for automatically providing feedback for introductory programming problems. In order to use this method, we need a reference implementation of the assignment, and an error model consisting of potential corrections to…

Common criticisms of state-of-the-art machine learning include poor generalisation, a lack of interpretability, and a need for large amounts of training data. We survey recent work in inductive logic programming (ILP), a form of machine…

Both professional coders and teachers frequently deal with imperfect (fragmentary, incomplete, ill-formed) code. Such fragments are common in STACKOVERFLOW; students also frequently produce ill-formed code, for which instructors, TAs (or…

Automated test case generation is important. However, the automatically generated test input does not always make sense, and the automated assertion is difficult to validate against the program under test. In this paper, we propose…

Authorship Verification (AV) is a text classification task concerned with inferring whether a candidate text has been written by one specific author or by someone else. It has been shown that many AV systems are vulnerable to adversarial…

This dissertation introduces executable refinement types, which refine structural types by semi-decidable predicates, and establishes their metatheory and accompanying implementation techniques. These results are useful for undecidable type…

Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle. They are prone to overfitting on their training distribution and are easily fooled by small adversarial perturbations. In this…

We demonstrate a method to infer polymorphically principal and subtyping-minimal types for an ML-like core language by assigning ranges within a lattice to type variables. We demonstrate the termination and completeness of this algorithm,…