Search Results (190)

Nanosatellites increasingly produce more data than can be downlinked within a reasonable time due to their limited bandwidth and power. Therefore, an on-board system is required to prioritize scientifically significant data for downlinking, as described by scientists. This paper determines whether natural language processing can be used to prioritize remote sensing images on CubeSats with more flexibility compared to existing methods. Two approaches implementing the same conceptual prioritization pipeline are compared. The first uses YOLOv8 and Llama2 to extract image features and compare them with text descriptions via cosine similarity. The second approach employs CLIP, fine-tuned on remote sensing data, to achieve the same. Both approaches are evaluated on real nanosatellite hardware, the VERTECS Camera Control Board. The CLIP approach, particularly the ResNet50-based model, shows the best performance in prioritizing and sequencing remote sensing images. This paper demonstrates that on-orbit prioritization using natural language descriptions is viable and allows for more flexibility than existing methods. Full article

With the development of artificial intelligence and deep learning technologies, image captioning has become an important research direction at the intersection of computer vision and natural language processing. The purpose of image captioning is to generate corresponding natural language descriptions by understanding the content of images. This technology has broad application prospects in fields such as image retrieval, autonomous driving, and visual question answering. Currently, many researchers have proposed region-based image captioning methods. These methods generate captions by extracting features from different regions of an image. However, they often rely on local features of the image and overlook the understanding of the overall scene, leading to captions that lack coherence and accuracy when dealing with complex scenes. Additionally, image captioning methods are unable to extract complete semantic information from visual data, which may lead to captions with biases and deficiencies. Due to these reasons, existing methods struggle to generate comprehensive and accurate captions. To fill this gap, we propose the Semantic Scenes Encoder (SSE) for image captioning. It first extracts a scene graph from the image and integrates it into the encoding of the image information. Then, it extracts a semantic graph from the captions and preserves semantic information through a learnable attention mechanism, which we refer to as the dictionary. During the generation of captions, it combines the encoded information of the image and the learned semantic information to generate complete and accurate captions. To verify the effectiveness of the SSE, we tested the model on the MSCOCO dataset. The experimental results show that the SSE improves the overall quality of the captions. The improvement in scores across multiple evaluation metrics further demonstrates that the SSE possesses significant advantages when processing identical images. Full article

Recent years have witnessed a rather controversial debate on what antioxidants are and how beneficial they may be in the context of human health. Despite a considerable increase in scientific evidence, the matter remains highly divisive as different pieces of new data seem to support both the pro- and the anti-antioxidant perspective. Here, we argue that the matter at the heart of this debate is not necessarily empirical but of semantics. Thus, the controversy cannot be resolved with the traditional tools of natural sciences and by the mere accumulation of new data. In fact, the term “antioxidants” has been part of the scientific language game for a few decades and is nowadays used differently in the context of different scientific disciplines active at different levels of scientific complexity. It, therefore, represents not a single expression but an entire family of words with distinctively different connotations and associations. The transcendent use of this expression from a basic to a more complex discipline, such as going from chemistry to physiology, is problematic as it assigns the term with connotations that are not corroborated empirically. This may lead to false claims and aspirations not warranted by empirical data. Initially, health claims may not even be indented, yet, on occasion, they are welcome for reasons other than scientific ones. To resolve this debate, one may need to refrain from using the term “antioxidants” in disciplines and contexts where its meaning is unclear, limit its use to disciplines where it is essential and beneficial, and, in any case, become more specific in such contexts where its use is warranted, for instance, in the case of “dietary antioxidants”. Full article

Large Language Models (LLMs) excel in fields such as natural language understanding, generation, complex reasoning, and biomedicine. With advancements in materials science, traditional manual annotation methods for phase diagrams have become inadequate due to their time-consuming nature and limitations in updating thermodynamic databases. To overcome these challenges, we propose a framework based on instruction tuning, utilizing LLMs for automated end-to-end annotation of phase diagrams. High-quality phase diagram images and expert descriptions are collected from handbooks and then preprocessed to correct errors, remove redundancies, and enhance information. These preprocessed data form a golden dataset, from which a subset are used to train LLMs through hierarchical sampling. The fine-tuned LLM is then tested for automated phase diagram annotation. Results show that the fine-tuned model achieves a cosine similarity of 0.8737, improving phase diagram comprehension accuracy by 7% compared to untuned LLMs. To the best of our knowledge, this is the first paper to propose using LLMs for the automated annotation of phase diagrams, replacing traditional manual annotation methods and significantly enhancing efficiency and accuracy. Full article

The Generative Pre-trained Transformer (GPT) is a highly advanced natural language processing model. This model can generate conversation-style responses to user input. The rapid rise of GPT has transformed academic domains, with studies exploring the potential of chatbots in education. This research investigates the effectiveness of ChatGPT 3.5, ChatGPT 4.0 by OpenAI, and Chatbot Bing by Microsoft in solving statistical exam-type problems in the educational setting. In addition to quantifying the errors made by these chatbots, this study seeks to understand the causes of these errors to provide recommendations. A mixed-methods approach was employed to achieve this goal, including quantitative and qualitative analyses (Grounded Theory with semi-structured interviews). The quantitative stage involves statistical problem-solving exercises for undergraduate engineering students, revealing error rates based on the reason for the error, statistical fields, sub-statistics fields, and exercise types. The quantitative analysis provided crucial information necessary to proceed with the qualitative study. The qualitative stage employs semi-structured interviews with selected chatbots; this includes confrontation between them that generates agreement, disagreement, and differing viewpoints. On some occasions, chatbots tend to maintain rigid positions, lacking the ability to adapt or acknowledge errors. This inflexibility may affect their effectiveness. The findings contribute to understanding the integration of AI tools in education, offering insights for future implementations and emphasizing the need for critical evaluation and responsible use. Full article

Natural language inference (NLI) is a fundamental and quite challenging task in natural language processing, requiring efficient methods that are able to determine whether given hypotheses derive from given premises. In this paper, we apply explainability techniques to natural-language-inference methods as a means to illustrate the decision-making procedure of its methods. First, we investigate the performance and generalization capabilities of several transformer-based models, including BERT, ALBERT, RoBERTa, and DeBERTa, across widely used datasets like SNLI, GLUE Benchmark, and ANLI. Then, we employ stacking-ensemble techniques to leverage the strengths of multiple models and improve inference performance. Experimental results demonstrate significant improvements of the ensemble models in inference tasks, highlighting the effectiveness of stacking. Specifically, our best-performing ensemble models surpassed the best-performing individual transformer by 5.31% in accuracy on MNLI-m and MNLI-mm tasks. After that, we implement LIME and SHAP explainability techniques to shed light on the decision-making of the transformer models, indicating how specific words and contextual information are utilized in the transformer inferences procedures. The results indicate that the model properly leverages contextual information and individual words to make decisions but, in some cases, find difficulties in inference scenarios with metaphorical connections which require deeper inferential reasoning. Full article

Tables serve as a widely adopted data format, attracting considerable academic interest concerning semantic understanding and logical inference of tables. In recent years, the prevailing paradigm of pre-training and fine-tuning on tabular data has become increasingly prominent in research on table understanding. However, existing table-based pre-training methods frequently exhibit constraints, supporting only single tasks while requiring substantial computational resources, which hinders their efficiency and applicability. In this paper, we introduce the TabMoE, a novel framework based on mixture-of-experts, designed to handle a wide range of tasks involving logical reasoning over tabular data. Each expert within the model specializes in a distinct logical function and is trained through the utilization of a hard Expectation–Maximization algorithm. Remarkably, this framework eliminates the necessity of dependency on tabular pre-training, instead exclusively employing limited task-specific data to significantly enhance models’ inferential capabilities. We conduct empirical experiments across three typical tasks related to tabular data: table-based question answering, table-based fact verification, and table-to-text generation. The experimental results underscore the innovation and feasibility of our framework. Full article

This research was conducted in 2019 in collaboration with Japanese colleagues, with the research tasks translated from the original Japanese. In Finland, a total of 1112 students from grades 7–9 in primary school participated in the study. In our article, we examine Finnish students’ mastery of the concept of percentages and how they express their mathematical thinking about percentages in a multimodal way. A multimodal expression of mathematical thinking can typically take the form of natural language, written mathematics, pictorial representations, mathematical symbolic language, or combinations of these, which can be used to manage information, such as through tables. Our focus is on Finnish primary-school students’ mastery of the concept of percentages, and we then narrow our analysis to tasks where students have used a multimodal approach. We analyze the representations of the concept of percentages and the related thought processes. The concept of percentages was best mastered in grade 9 and weakest in grade 7. Students mostly used a combination of pictorial language, natural language, and mathematical symbolic language to describe their solution processes. However, describing their thinking in different ways did not necessarily highlight possible errors in their reasoning. Full article

Data augmentation is crucial for enhancing the performance of text classification models when labelled training data are scarce. For natural language processing (NLP) tasks, large language models (LLMs) are able to generate high-quality augmented data. But a fundamental understanding of the reasons for their effectiveness remains limited. This paper presents a geometric and topological perspective on textual data augmentation using LLMs. We compare the augmentation data generated by GPT-J with those generated through cosine similarity from Word2Vec and GloVe embeddings. Topological data analysis reveals that GPT-J generated data maintains label coherence. Convex hull analysis of such data represented by their two principal components shows that they lie within the spatial boundaries of the original training data. Delaunay triangulation reveals that increasing the number of augmented data points that are connected within these boundaries correlates with improved classification accuracy. These findings provide insights into the superior performance of LLMs in data augmentation. A framework for predicting the usefulness of augmentation data based on geometric properties could be formed based on these techniques. Full article

Network security policy is regarded as a guideline for the use and management of the network environment, which usually formulates various requirements in the form of natural language. It can help network managers conduct standardized network attack detection and situation awareness analysis in the overall time and space environment of network security. However, in most cases, due to configuration updates or policy conflicts, there are often differences between the real network environment and network security policies. In this case, the consistency detection of network security policies is necessary. The previous consistency detection methods of security policies have some problems. Firstly, the detection direction is single, only focusing on formal reasoning methods to achieve logical consistency detection and solve problems. Secondly, the detection policy field is not comprehensive, focusing only on a certain type of problem in a certain field. Thirdly, there are numerous forms of data structures used for consistency detection, and it is difficult to unify the structured processing and analysis of rule library carriers and target information carriers. With the development of intelligent graph and data mining technology, the above problems have the possibility of optimization. This article proposes a new consistency detection approach for network security policy, which uses an intelligent graph database as a visual information carrier, which can widely connect detection information and achieve comprehensive detection across knowledge domains, physical devices, and detection methods. At the same time, it can also help users grasp the security associations with the real network environment based on the graph algorithm of the knowledge graph and intelligent reasoning. Furthermore, these actual network situations and knowledge bases can help managers improve policies more tailored to local conditions. This article also introduces the consistency detection process of typical cases of network security policies, demonstrating the practical details and effectiveness of this method. Full article

In the information age, semantic parsing technology drives efficiency improvement and accelerates the process of intelligence. However, it faces complex understanding, data inflation, inappropriate evaluation, and difficult application of advanced large models. This study analyses the current challenges and looks forward to the development trend of the technology. Specific approaches include: this study adopts a systematic review method and strictly follows the PRISMA framework, deeply analyzes the key ideas, methods, problems, and solutions of traditional and neural network methods, and explores the model performance, API application, dataset, and evaluation mechanism. Through literature analysis, the technology is classified according to its application scenarios. Then, the practical application contributions are summarized, current limitations such as data size, model performance, and resource requirements are analyzed, and future directions such as dataset expansion, real-time performance enhancement, and industrial applications are envisioned. The results of the study show significant advances in semantic parsing technology with far-reaching impacts. Traditional and neural network methods complement each other to promote theoretical and practical innovation. In the future, with the continuous progress and in-depth application of machine learning technology, semantic parsing technology needs to further deepen the research on logical reasoning and evaluation, to better cope with technical challenges and lead the new development of natural language processing and AI. Full article

The incorporation of Artificial Intelligence (AI) models into various optimization systems is on the rise. However, addressing complex urban and environmental management challenges often demands deep expertise in domain science and informatics. This expertise is essential for deriving data and simulation-driven insights that support informed decision-making. In this context, we investigate the potential of leveraging the pre-trained Large Language Models (LLMs) to create knowledge representations for supporting operations research. By adopting ChatGPT-4 API as the reasoning core, we outline an applied workflow that encompasses natural language processing, Methontology-based prompt tuning, and Generative Pre-trained Transformer (GPT), to automate the construction of scenario-based ontologies using existing research articles and technical manuals of urban datasets and simulations. From these ontologies, knowledge graphs can be derived using widely adopted formats and protocols, guiding various tasks towards data-informed decision support. The performance of our methodology is evaluated through a comparative analysis that contrasts our AI-generated ontology with the widely recognized pizza ontology, commonly used in tutorials for popular ontology software. We conclude with a real-world case study on optimizing the complex system of multi-modal freight transportation. Our approach advances urban decision support systems by enhancing data and metadata modeling, improving data integration and simulation coupling, and guiding the development of decision support strategies and essential software components. Full article

This paper explores the performance of ChatGPT and GeoGebra Discovery when dealing with automatic geometric reasoning and discovery. The emergence of Large Language Models has attracted considerable attention in mathematics, among other fields where intelligence should be present. We revisit a couple of elementary Euclidean geometry theorems discussed in the birth of Artificial Intelligence and a non-trivial inequality concerning triangles. GeoGebra succeeds in proving all these selected examples, while ChatGPT fails in one case. Our thesis is that both GeoGebra and ChatGPT could be used as complementary systems, where the natural language abilities of ChatGPT and the certified computer algebra methods in GeoGebra Discovery can cooperate in order to obtain sound and—more relevant—interesting results. Full article

In the field of Natural Language Processing (NLP), the lack of support for minority languages, especially Uyghur, the scarcity of Uyghur language corpora in the agricultural domain, and the lightweight nature of large language models remain prominent issues. This study proposes a method for constructing a bilingual (Uyghur and Chinese) lightweight specialized large language model for the agricultural domain. By utilizing a mixed training approach of Uyghur and Chinese, we extracted Chinese corpus text from agricultural-themed books in PDF format using OCR (Optical Character Recognition) technology, converted the Chinese text corpus into a Uyghur corpus using a rapid translation API, and constructed a bilingual mixed vocabulary. We applied the parameterized Transformer model algorithm to train the model for the agricultural domain in both Chinese and Uyghur. Furthermore, we introduced a context detection and fail-safe mechanism for the generated text. The constructed model possesses the ability to support bilingual reasoning in Uyghur and Chinese in the agricultural domain, with higher accuracy and a smaller size that requires less hardware. It (our work) addresses issues such as the scarcity of Uyghur corpora in the agricultural domain, mixed word segmentation and word vector modeling in Uyghur for widespread agricultural languages, model lightweighting and deployment, and the fragmentation of non-relevant texts during knowledge extraction from small-scale corpora. The lightweight design of the model reduces hardware requirements, facilitating deployment in resource-constrained environments. This advancement promotes agricultural intelligence, aids in the development of specific applications and minority languages (such as agriculture and Uyghur), and contributes to rural revitalization. Full article

AI chatbots have emerged as powerful tools for providing text-based solutions to a wide range of everyday challenges. Selecting the appropriate chatbot is crucial for optimising outcomes. This paper presents a comprehensive comparative analysis of five leading chatbots: ChatGPT, Bard, Llama, Ernie, and Grok. The analysis is based on a systematic review of 28 scholarly articles. The review indicates that ChatGPT, developed by OpenAI, excels in educational, medical, humanities, and writing applications but struggles with real-time data accuracy and lacks open-source flexibility. Bard, powered by Google, leverages real-time internet data for problem solving and shows potential in competitive quiz environments, albeit with performance variability and inconsistencies in responses. Llama, an open-source model from Meta, demonstrates significant promise in medical contexts, natural language processing, and personalised educational tools, yet it requires substantial computational resources. Ernie, developed by Baidu, specialises in Chinese language tasks, thus providing localised advantages that may not extend globally due to restrictive policies. Grok, developed by Xai and still in its early stages, shows promise in providing engaging, real-time interactions, humour, and mathematical reasoning capabilities, but its full potential remains to be evaluated through further development and empirical testing. The findings underscore the context-dependent utility of each model and the absence of a singularly superior chatbot. Future research should expand to include a wider range of fields, explore practical applications, and address concerns related to data privacy, ethics, security, and the responsible deployment of these technologies. Full article