Related papers: Diverse Title Generation for Stack Overflow Posts …
In an era of widespread influence of Natural Language Processing (NLP), there have been multiple research efforts to supplant traditional manual coding techniques with automated systems capable of generating solutions autonomously. With…
We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…
Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a…
We study the task of long-form opinion text generation, which faces at least two distinct challenges. First, existing neural generation models fall short of coherence, thus requiring efficient content planning. Second, diverse types of…
Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive…
Graphs model several real-world phenomena. With the growth of unstructured and semi-structured data, parallelization of graph algorithms is inevitable. Unfortunately, due to inherent irregularity of computation, memory access, and…
Software developers often reuse code from online sources such as Stack Overflow within their projects. However, the process of searching for code snippets and integrating them within existing source code can be tedious. In order to improve…
Stack Overflow (SO) is the most popular question-and-answer website for software developers, providing a large amount of code snippets and free-form text on a wide variety of topics. Like other software artifacts, questions and answers on…
Language Models (LMs) are increasingly challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs), in graph learning tasks. Following this trend, we propose a novel approach that…
Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…
Developers often resort to online Q&A forums such as Stack Overflow (SO) for filling their programming needs. Although code examples on those forums are good starting points, they are often incomplete and inadequate for developers' local…
We consider the end-to-end abstract-to-title generation problem, exploring seven recent transformer based models (including ChatGPT) fine-tuned on more than 30k abstract-title pairs from NLP and machine learning (ML) venues. As an…
Detecting AI-generated code, deepfakes, and other synthetic content is an emerging research challenge. As code generated by Large Language Models (LLMs) becomes more common, identifying the specific model behind each sample is increasingly…
Code search and comprehension have become more difficult in recent years due to the rapid expansion of available source code. Current tools lack a way to label arbitrary code at scale while maintaining up-to-date representations of new…
Prior work on automated question generation has almost exclusively focused on generating simple questions whose answers can be extracted from a single document. However, there is an increasing interest in developing systems that are capable…
Building effective text generation systems requires three critical components: content selection, text planning, and surface realization, and traditionally they are tackled as separate problems. Recent all-in-one style neural generation…
Evaluating LLMs with a single prompt has proven unreliable, with small changes leading to significant performance differences. However, generating the prompt variations needed for a more robust multi-prompt evaluation is challenging,…
Multiscale feature hierarchies have been witnessed the success in the computer vision area. This further motivates researchers to design multiscale Transformer for natural language processing, mostly based on the self-attention mechanism.…
A great video title describes the most salient event compactly and captures the viewer's attention. In contrast, video captioning tends to generate sentences that describe the video as a whole. Although generating a video title…
Existing research on news summarization primarily focuses on single-language single-document (SLSD), single-language multi-document (SLMD) or cross-language single-document (CLSD). However, in real-world scenarios, news about a…