Related papers: SUT: Active Defects Probing for Transcompiler Mode…
Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly…
Speech-to-Speech Translation (S2ST) refers to the conversion of speech in one language into semantically equivalent speech in another language, facilitating communication between speakers of different languages. Speech-to-Discrete Unit…
When employing the Socratic method of teaching, instructors guide students toward solving a problem on their own rather than providing the solution directly. While this strategy can substantially improve learning outcomes, it is usually…
The high-quality translation results produced by machine translation (MT) systems still pose a huge challenge for automatic evaluation. Current MT evaluation pays the same attention to each sentence component, while the questions of…
Despite recent successes with neural models for sign language translation (SLT), translation quality still lags behind spoken languages because of the data scarcity and modality gap between sign video and text. To address both problems, we…
Despite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes…
Software is omnipresent within all factors of society. It is thus important to ensure that software are well tested to mitigate bad user experiences as well as the potential for severe financial and human losses. Software testing is however…
Traditional static analysis methods struggle to detect semantic design flaws, such as violations of the SOLID principles, which require a strong understanding of object-oriented design patterns and principles. Existing solutions typically…
Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to new compositions/structures that have not…
During software maintenance, programmers spend a lot of time on code comprehension. Reading comments is an effective way for programmers to reduce the reading and navigating time when comprehending source code. Therefore, as a critical task…
Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task. In this work, we present a system called AutoNLU, which we designed to…
Generative Pre-Trained Transformer models have been shown to be surprisingly effective at a variety of natural language processing tasks -- including generating computer code. We evaluate the effectiveness of open source GPT models for the…
Continual learning has emerged as an increasingly important challenge across various tasks, including Spoken Language Understanding (SLU). In SLU, its objective is to effectively handle the emergence of new concepts and evolving…
A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages. However, the literature suggests that many obstacles must still be dealt with to achieve better…
Modern programming languages (e.g., Java and C#) provide features to separate error-handling code from regular code, seeking to enhance software comprehensibility and maintainability. Nevertheless, the way exception handling (EH) code is…
The Software Naturalness hypothesis argues that programming languages can be understood through the same techniques used in natural language processing. We explore this hypothesis through the use of a pre-trained transformer-based language…
Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so we generally need multiple tokens to express a complete…
Automatic code generation is to generate the program code according to the given natural language description. The current mainstream approach uses neural networks to encode natural language descriptions, and output abstract syntax trees…
A central question in natural language understanding (NLU) research is whether high performance demonstrates the models' strong reasoning capabilities. We present an extensive series of controlled experiments where pre-trained language…
Proof-oriented programs mix computational content with proofs of program correctness. However, the human effort involved in programming and proving is still substantial, despite the use of Satisfiability Modulo Theories (SMT) solvers to…