相关论文: What model(s) for program understanding?

Modeling long texts has been an essential technique in the field of natural language processing (NLP). With the ever-growing number of long documents, it is important to develop effective modeling methods that can process and analyze such…

Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or…

Affects---emotions and moods---have an impact on cognitive activities and the working performance of individuals. Development tasks are undertaken through cognitive processes, yet software engineering research lacks theory on affects and…

Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a…

In this paper, we investigate the following question: how could you write such computer programs that can work like conscious beings? The motivation behind this question is that we want to create such applications that can see the future.…

This paper is about a new way for programming distributed applications: the service-oriented one. It is a concept paper based upon our experience in developing a theory and a language for programming services. Both the theoretical…

Cognitive tasks originally developed for humans are now increasingly used to study language models. While applying these tasks is often straightforward, interpreting their results can be challenging. In particular, when a model…

Mechanistic interpretability focuses on reverse engineering the internal mechanisms learned by neural networks. We extend our focus and propose to mechanistically forward engineer using our framework based on Concept Bottleneck Models. In…

The purpose of a program analysis is to compute an abstract meaning for a program which approximates its dynamic behaviour. A compositional program analysis accomplishes this task with a divide-and-conquer strategy: the meaning of a program…

Knowing others' intentions and taking others' perspectives are two core components of human intelligence that are considered to be instantiations of theory-of-mind. Infiltrating machines with these abilities is an important step towards…

This report describes de design of an experiment that intends to compare two variants of a modeldriven system development method, so as to assess the impact of requirements engineering practice in the quality of the conceptual models. The…

Programming is an integral part of computer science discipline. Every day the programming environment is not only rapidly growing but also changing and languages are constantly evolving. Learning of object-oriented paradigm is compulsory in…

Two-dimensional patterns are used in many research areas in computer science, ranging from image processing to specification and verification of complex software systems (via scenarios). The contribution of this paper is twofold. First, we…

When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. Most deep network based agent-modeling approaches are 1) not interpretable…

Models of object vision have been of great interest in computer vision and visual neuroscience. During the last decades, several models have been developed to extract visual features from images for object recognition tasks. Some of these…

We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of…

In the last years many results in the area of semidefinite programming were obtained for invariant (finite dimensional, or infinite dimensional) semidefinite programs - SDPs which have symmetry. This was done for a variety of problems and…

Excellent computer simulations are done for a purpose. The most valid purposes are to explore uncharted territory, to resolve a well-posed scientific or technical question, or to make a design choice. Stand-alone modeling can serve the…

Understanding narrative text requires capturing characters' motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal-states of characters in a story. We explicitly model…