Related papers: Technical Report on Neural Language Models and Few…

The Fourth International Workshop on Domain-Specific Languages and Models for Robotic Systems (DSLRob'13) was held in conjunction with the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), November 2013…

Language models (LMs) are often expected to generate strings in some formal language; for example, structured data, API calls, or code snippets. Although LMs can be tuned to improve their adherence to formal syntax, this does not guarantee…

Few-shot learning (FSL) has attracted considerable attention recently. Among existing approaches, the metric-based method aims to train an embedding network that can make similar samples close while dissimilar samples as far as possible and…

The analysis of software requirement specifications (SRS) using Natural Language Processing (NLP) methods has been an important study area in the software engineering field in recent years. Especially thanks to the advances brought by deep…

[Context & motivation] Eliciting requirements that are detailed and logical enough to be amenable to formal verification is a difficult task. Multiple tools exist for requirements elicitation and some of these also support formalisation of…

Event detection (ED) is aimed to identify the key trigger words in unstructured text and predict the event types accordingly. Traditional ED models are too data-hungry to accommodate real applications with scarce labeled data. Besides,…

Recently, Large language models (LLMs) with in-context learning have demonstrated remarkable potential in handling neural machine translation. However, existing evidence shows that LLMs are prompt-sensitive and it is sub-optimal to apply…

Addressing the challenge of limited annotated data in specialized fields and low-resource languages is crucial for the effective use of Language Models (LMs). While most Large Language Models (LLMs) are trained on general-purpose English…

Context: Machine Learning (ML) has become widely adopted as a component in many modern software applications. Due to the large volumes of data available, organizations want to increasingly leverage their data to extract meaningful insights…

Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number…

For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of…

While NMT has achieved remarkable results in the last 5 years, production systems come with strict quality requirements in arbitrarily niche domains that are not always adequately covered by readily available parallel corpora. This is…

LLMs are typically trained in high-resource languages, and tasks in lower-resourced languages tend to underperform the higher-resource language counterparts for in-context learning. Despite the large body of work on prompting settings, it…

Large language models (LLMs) have demonstrated strong capabilities in generating executable code from natural language descriptions. However, general-purpose models often struggle in specialized programming contexts where domain-specific…

As cyber threats become more sophisticated, rapid and accurate vulnerability detection is essential for maintaining secure systems. This study explores the use of Large Language Models (LLMs) in software vulnerability assessment by…

Recent studies have revealed the intriguing few-shot learning ability of pretrained language models (PLMs): They can quickly adapt to a new task when fine-tuned on a small amount of labeled data formulated as prompts, without requiring…

This paper contributes to speeding up the design and deployment of engineering dynamical systems by proposing a strategy for exploiting domain and expert knowledge for the automated generation of a dynamical system computational model…

Requirements expressed in natural language are an indispensable artifact in the software development process, as all stakeholders can understand them. However, their ambiguity poses a persistent challenge. To address this issue,…

Despite cross-lingual generalization demonstrated by pre-trained multilingual models, the translate-train paradigm of transferring English datasets across multiple languages remains to be a key mechanism for training task-specific…

Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to…