相关论文: Learning to Mine Aligned Code and Natural Language…

Optimizing scientific software is a difficult task because codebases are often large and complex, and performance can depend upon several factors including the algorithm, its implementation, and hardware among others. Causes of poor…

Training LLMs on data containing unfamiliar knowledge during the instruction tuning stage can encourage hallucinations. To address this challenge, we introduce NOVA, a novel framework designed to identify high-quality data that aligns well…

Given a closed-source program, such as most of proprietary software and viruses, binary code analysis is indispensable for many tasks, such as code plagiarism detection and malware analysis. Today, source code is very often compiled for…

The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also…

While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set…

Word alignments are useful for tasks like statistical and neural machine translation (NMT) and cross-lingual annotation projection. Statistical word aligners perform well, as do methods that extract alignments jointly with translations in…

Entity matching is the task of linking records from different sources that refer to the same real-world entity. Past work has primarily treated entity linking as a standard supervised learning problem. However, supervised entity matching…

Code summarization is the task of generating natural language description of source code, which is important for program understanding and maintenance. Existing approaches treat the task as a machine translation problem (e.g., from Java to…

The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or…

Stack Overflow has been heavily used by software developers to seek programming-related information. More and more developers use Community Question and Answer forums, such as Stack Overflow, to search for code examples of how to accomplish…

We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our approach does not…

Fact verification aims to verify a claim using evidence from a trustworthy knowledge base. To address this challenge, algorithms must produce features for every claim that are both semantically meaningful, and compact enough to find a…

We introduce "pointer-guided segment ordering" (SO), a novel pre-training technique aimed at enhancing the contextual understanding of paragraph-level text representations in large language models. Our methodology leverages a…

Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing (NLP) tasks, primarily through in-context learning (ICL). In ICL, the LLM is provided with examples that represent a given…

The ability to reason with natural language is a fundamental prerequisite for many NLP tasks such as information extraction, machine translation and question answering. To quantify this ability, systems are commonly tested whether they can…

Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. The current approaches mainly involve hard-coded, rule-based systems…

The success of Large Language Models (LLMs) in various domains has led researchers to apply them to graph-related problems by converting graph data into natural language text. However, unlike graph data, natural language inherently has…

The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which…

Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of a prompt, two different responses to the prompt, and a binary label indicating which of the two…

With the growing popularity of code-mixed data, there is an increasing need for better handling of this type of data, which poses a number of challenges, such as dealing with spelling variations, multiple languages, different scripts, and a…