Related papers: Converting Epics/Stories into Pseudocode using Tra…
Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates…
The task of generating code solutions for a given programming problem can benefit from the use of pre-trained language models such as Codex, which can produce multiple diverse samples. However, a major challenge for this task is to select…
Decompilation is a well-studied area with numerous high-quality tools available. These are frequently used for security tasks and to port legacy code. However, they regularly generate difficult-to-read programs and require a large amount of…
In this work, we train an Automatic Post-Editing (APE) model and use it to reveal biases in standard Machine Translation (MT) evaluation procedures. The goal of our APE model is to correct typical errors introduced by the translation…
In software development, it is common for programmers to copy-paste or port code snippets and then adapt them to their use case. This scenario motivates the code adaptation task -- a variant of program repair which aims to adapt variable…
Computer-Aided Design (CAD) models are typically constructed by sequentially drawing parametric sketches and applying CAD operations to obtain a 3D model. The problem of 3D CAD reverse engineering consists of reconstructing the sketch and…
A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts. Although contemporary text encoding methods cover most of the world's writing systems, they exhibit bias…
Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing approaches augment reasoning steps or inject specific structure into how models think, but…
Code super-optimization is the task of transforming any given program to a more efficient version while preserving its input-output behaviour. In some sense, it is similar to the paraphrase problem from natural language processing where the…
Recently, smart contracts have played a vital role in automatic financial and business transactions. To help end users without programming background to better understand the logic of smart contracts, previous studies have proposed models…
Symbolic Execution is a formal method that can be used to verify the behavior of computer programs and detect software vulnerabilities. Compared to other testing methods such as fuzzing, Symbolic Execution has the advantage of providing…
Code translation is one of the core capabilities of LLMs. However, evaluating the correctness of translations remains difficult, as commonly used metrics such as BLEU measure only syntactic similarity, disregarding program semantics. We…
Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and…
In recent years, Large Language Models (LLMs) have dramatically advanced the performance of automated code translation, making their computational accuracy score reach up to over 80% on many previous benchmarks. However, most code samples…
This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units. We view the subword segmentation of output sentences as a latent variable that should be marginalized out…
Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…
When building state-of-the-art speech translation models, the need for large computational resources is a significant obstacle due to the large training data size and complex models. The availability of pre-trained models is a promising…
Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, token-free models that operate directly on raw text (bytes or characters) have many benefits: they can…
Changes in source code are an inevitable part of software development. They are the results of indispensable activities such as fixing bugs or improving functionality. Descriptions for code changes (commit messages) help people better…
The development of a real-time web application often starts with a feature-driven approach allowing to quickly react to users feedbacks. However, this approach poorly scales in performance. Yet, the user-base can increase by an order of…