Pre-trained Transformers are challenging human performances in many NLP tasks. The massive datasets used for pre-training seem to be the key to their success on existing tasks. In this paper, we explore how a range of...
This paper presents an educational activity developed within the AIM@VET project, aimed at integrating Large language Models (LLMs) into Vocational Education and Training (VET) for programming robots using natural lan...
详细信息
ISBN:
(纸本)9783031777370;9783031777387
This paper presents an educational activity developed within the AIM@VET project, aimed at integrating Large language Models (LLMs) into Vocational Education and Training (VET) for programming robots using naturallanguage. The curriculum covers key AI topics such as Human-Robot Interaction (HRI), naturallanguageprocessing, and the use of advanced models like ChatGPT. Students engage in activities from basic command interpretation to advanced voice-controlled interactions, gaining practical experience with LLMs in robotics. Evaluations showed significant improvements in understanding and engagement, highlighting the effectiveness of LLMs in enhancing robotics education for VET students.
The iterative nature of agile requirements engineering often requires considerable time and effort. Research on automation processes with artificial intelligence for agile requirements engineering practices has gained...
详细信息
Recent technologies like ChatGPT inspire ideas of increasing automation for professional tasks in various domains. This includes among others requirements engineering. So far, however, the divide between useful and ha...
详细信息
ISBN:
(纸本)9798350395129;9798350395112
Recent technologies like ChatGPT inspire ideas of increasing automation for professional tasks in various domains. This includes among others requirements engineering. So far, however, the divide between useful and harmful automation has been blurry and in flux. In this keynote, I will discuss foundational concepts with which automation has been analyzed. Using these concepts, I will discuss the opportunities arising for requirements engineering from the advent of naturallanguageprocessing, image processing, and event sequence analysis techniques. Furthermore, I will discuss important pitfalls that have been well documented for other automation technologies in the past.
Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used i...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of them are trained on web-crawled general-purpose datasets, which incurs a considerable domain gap when used for VLN tasks. To address the problem, we propose a novel and model-agnostic Domain-Aware Prompt learning (DAP) framework. For equipping the pretrained models with specific object-level and scene-level cross-modal alignment in VLN tasks, DAP applies a low-cost prompt tuning paradigm to learn soft visual prompts for extracting in-domain image semantics. Specifically, we first generate a set of in-domain image-text pairs with the help of the CLIP model. Then we introduce soft visual prompts in the input space of the visual encoder in a pretrained model. DAP injects in-domain visual knowledge into the visual encoder of the pretrained model in an efficient way. Experimental results on both R2R and REVERIE show the superiority of DAP compared to existing state-of-the-art methods.
Since reading and responding to text needs both a grasp of naturallanguage and awareness of the outside world, it is challenging for machines to do [1]. The most difficult areas of information retrieval and natural l...
详细信息
Complex naturallanguage texts affect the accuracy of information extraction and semantic understanding. To address this problem, this paper applies the attention mechanism to make full use of contextual information t...
详细信息
Alzheimer's Disease and Related Dementias (ADRD) patients and older adults face challenges related to memory loss, navigation difficulties, and social isolation, impacting their daily tasks, appointments, and soci...
详细信息
ISBN:
(纸本)9798350385328;9798350385335
Alzheimer's Disease and Related Dementias (ADRD) patients and older adults face challenges related to memory loss, navigation difficulties, and social isolation, impacting their daily tasks, appointments, and social connections. To address these multifaceted challenges, this paper presents the design, development, and preliminary evaluation of "CareCompanion," a virtual assistant tailored specifically for this population. Leveraging advanced AI technologies such as naturallanguageprocessing, machine learning, and knowledge graphs, CareCompanion provides personalized reminders, navigation assistance, and social connectivity features. Preliminary evaluation results demonstrate the potential of CareCompanion in improving the quality of life, independence, and social engagement for ADRD patients and older adults. Further research and development can enhance its effectiveness, usability, and customization, catering to the unique needs of this population, while fostering connections and mitigating the impact of memory loss, navigation difficulties, and social isolation.
It might be intimidating to navigate the wide array of learning resources in this era of information overload. This article presents knowledge Navigator, an artificial intelligence (AI) system that adapts the learning...
详细信息
Ophthalmic disease zero-shot question answering aims to answer questions about ophthalmic disease in naturallanguage without any model training. Although the pretrained large language models (LLMs) have stored quanti...
详细信息
暂无评论