Related papers: The Code2Text Challenge: Text Generation in Source…
The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to…
Existing source-code-generating tools such as Lex and Yacc suffer from practical inconveniences because they use disembodied code to implement actions. To prevent this problem, such tools could generate closed functors that are then…
Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning…
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like…
This work delved into the realm of automatic text generation, exploring a variety of techniques ranging from traditional deterministic approaches to more modern stochastic methods. Through analysis of greedy search, beam search, top-k…
Users interact with text, image, code, or other editors on a daily basis. However, machine learning models are rarely trained in the settings that reflect the interactivity between users and their editor. This is understandable as training…
An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural…
One of the biggest challenges of end-to-end language generation from meaning representations in dialogue systems is making the outputs more natural and varied. Here we take a large corpus of 50K crowd-sourced utterances in the restaurant…
As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code…
The topic-to-essay generation task is a challenging natural language generation task that aims to generate paragraph-level text with high semantic coherence based on a given set of topic words. Previous work has focused on the introduction…
The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast amounts of labor to keep them tested, maintained, and up to date. As the…
Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on…
Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge graphs or wiki…
Due to the development of pre-trained language models, automated code generation techniques have shown great promise in recent years. However, the generated code is difficult to meet the syntactic constraints of the target language,…
Many programmers, when they encounter an error, would like to have the benefit of automatic fix suggestions---as long as they are, most of the time, adequate. Initial research in this direction has generally limited itself to specific…
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and…
Generating fake data is an essential dimension of modern software testing, as demonstrated by the number and significance of data faking libraries. Yet, developers of faking libraries cannot keep up with the wide range of data to be…
Code summary generation is the task of writing natural language descriptions of a section of source code. Recent advances in Large Language Models (LLMs) and other AI-based technologies have helped make automatic code summarization a…
The problem of code generation from textual program descriptions has long been viewed as a grand challenge in software engineering. In recent years, many deep learning based approaches have been proposed, which can generate a sequence of…
We consider the problem of developing suitable learning representations (embeddings) for library packages that capture semantic similarity among libraries. Such representations are known to improve the performance of downstream learning…