检索结果-内蒙古大学图书馆

40th Annual Conference of the Spanish Association for Natural Language Processing, SEPLN-P 2024

作者： Botella-Gil, Beatriz Bonet-Jover, Alba Sepúlveda-Torres, Robiert Martínez-Barco, Patricio Saquete, Estela Department of Software and Computing Systems University of Alicante Spain

Natural Language Processing (NLP) has become an essential tool for the automatic detection of violent language and unreliable information. The misuse of Information and Communication Technologies (ICTs) fosters the generation of disinformation and digital violence, thus polarising society. Furthermore, the lack of reliable, neutral and accurate language when presenting news can trigger an increase in negative and violent users’ reactions. It is necessary to find a linkage between disinformation and violent discourse in order to moderate online content, facilitate early detection of both phenomena and ensure healthy online behaviour. This research uses NLP techniques to explore the reliability of news headlines and their correlation with violent language generated in comments by users. In addition, the generation of a novel resource annotated in Spanish is created to jointly address the automatic detection of violent language and reliability. © 2024 Copyright for this paper by its authors.

关键词： Data analysis Natural Language Processing Reliability detection Violent language

来源：评论

学校读者我要写书评

暂无评论

Exploring Content-Based Catalogs for Enhanced Discovery Services in Data Spaces 27

Exploring Content-Based Catalogs for Enhanced Discovery Serv...

引用

27th International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data, DOLAP 2025

作者： Morejón, Adriana Berenguer, Alberto de Espona, Lucía Tomás, David Mazón, Jose-Norberto University Institute for Computing Research Department of Software and Computing Systems University of Alicante Spain

In the realm of data sharing, effective data discovery is critical for fostering collaboration and innovation across organizations. Data spaces merge the interoperability and secure sharing features of data ecosystems with the transactional and economic aspects of data markets, enabling seamless data exchange among data providers and consumers while preserving data sovereignty. Central to this paradigm is the data catalog, an entity that handles metadata and provides it for data discovery services. However, traditional data catalogs rely heavily on metadata related to high-level representation of data, as well as the overall features of datasets (e.g., dataset name, license or keywords, following standards such as DCAT). This limitation hampers data discovery, as these metadata alone may not effectively describe datasets to fully convey the relevance of datasets. To address this challenge, this paper proposes content-based catalogs to enhance data discovery within data spaces. Our approach for content-based catalogs incorporates three key assets for data consumers to discover relevant datasets and evaluate their utility before accessing them: (i) high-quality structural metadata for datasets;(ii) representative data samples from the dataset;and (iii) a discovery service for searching relevant datasets. Our novel content-based catalog reduces the risk of unintended exposure while still showcasing the value of data, thus preserving the interests of both data providers and consumers within data spaces. © 2025 Copyright for this paper by its authors.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing Models for Knowledge Discovery in Medical Texts 7

Natural Language Processing Models for Knowledge Discovery i...

引用

7th Doctoral Symposium on Natural Language Processing, NLP-DS 2024

作者： Grande, Eduardo Department of Software and Computing Systems University of Alicante Spain

Electronic Health Records (EHRs) contain vast amounts of valuable information about patients’ diseases, diagnoses, or medications, mostly in an unstructured format. Recently, Large Language Models (LLMs), particularly generative models, have gained popularity due to their remarkable capabilities. This PhD thesis aims to harness the power of these models for the medical field, specifically for knowledge extraction tasks. The goal is to adjust NLP models to extract critical insights from EHRs and other medical texts. However, one of the main challenges is the limited availability of publicly accessible medical data, especially annotated datasets in languages other than English. In order to adjust the models, the thesis explores various adaptation techniques, including prompt-tuning or continual pre-training to enhance the models’ ability to process medical information effectively. Additionally, it evaluates different LLM architectures to determine the most suitable for medical knowledge extraction. Innovative strategies like LoRA (Low-Rank Adaptation) and QLoRA (Quantized LoRA) are also investigated to try to improve efficiency. The outcomes of this research hold the potential to significantly enhance healthcare delivery and and help practitioners quickly understand patient data. © 2024 Copyright for this paper by its authors.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Can Natural Language Processing Technologies Help the Digital Transformation of Local Public Administrations? 7

Can Natural Language Processing Technologies Help the Digita...

引用

7th Doctoral Symposium on Natural Language Processing, NLP-DS 2024

作者： Lloret, Ángel Department of Software and Computing Systems University of Alicante Alicante03690 Spain

In this article, we present an investigation with its conclusions and results on the pivotal role of Natural Language Processing (NLP) technologies in the ongoing digital transformation of our society, specifically within local public administrations. Our research is focused on the utilization of chatbots as tools for interaction, information retrieval, and provision, which we justify as the central objective to our study. This advanced tool facilitates the acquisition of crucial information for public managers regarding usage patterns, behaviors, statistics, and other data collected from citizens, tourists, or other groups interacting with their local public administration. Monitoring will be conducted via indicators and data compiled in a control panel or dashboard, aiding data-driven decision-making, enhancing user experience, and increasing satisfaction. The justification for employing chatbots as a communication channel lies in their simplicity, ease of understanding, and user-friendly nature. Key contributions of this NLP tool include the selection, compilation, and classification of datasets, as well as the provision of various functionalities (such as search, reading comprehension, chat, recommendation, and classification) that ensure users receive the requested information with the highest possible accuracy. The research based on the hypothesis outlined below will ultimately confirm the results presented in this study affirmatively answer the question posed in the title of the article. © 2024 Copyright for this paper by its authors.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Entity Modelling through Ontologies and Large Language Models 6

Entity Modelling through Ontologies and Large Language Model...

引用

6th Doctoral Symposium on Natural Language Processing from the Proyecto ILENIA, PLN-DS 2023

作者： Yáñez-Romero, Fabio Antonio Department of Software and Computing Systems University of Alicante Spain

The aim of this paper is to present a line of research focused on improving the knowledge represented in natural language processing tasks through the use of ontologies, combining these with machine learning techniques. It is expected that with this kind of techniques it will be possible to fight against phenomena such as the hallucination present in current generative language models and to reach the state of the art in different tasks taking into account semantic knowledge. Initially, we will try to solve the problem of semantics in specific areas such as medicine, where the external knowledge that can be incorporated would help to provide knowledge that does not exist in unstructured data such as all ICD-10 codes. Therefore, we expect obtain enough conclusions to apply this methodology with other dominions. © 2021 Copyright for this paper by its authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Weakly-Supervised Approach for Layout Analysis in Music Score Images 11th

A Weakly-Supervised Approach for Layout Analysis in Music ...

引用

11th Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2023

作者： Ayllon, Eric Castellanos, Francisco J. Calvo-Zaragoza, Jorge Department of Software and Computing Systems University of Alicante Alicante Spain

ISBN: (纸本)9783031366154

In this paper, we propose a data-efficient holistic method for layout analysis in the context of Optical Music Recognition (OMR). Our approach can be trained by just providing the number of staves present in the document collection at issue (weak label), thereby making it practical for real use cases where other fine-grained annotations are expensive. We consider a Convolutional Recurrent Neural Network trained with the Connectionist Temporal Classification loss function, which must retrieve a pretext sequence that encodes the number of staves per page. As a by-product, the model learns to relate every image row according to the presence or not of a staff. We demonstrate that our approach achieves performances close to the full supervised scenario on two OMR benchmarks, according to the eventual performance of the full transcription pipeline. We believe that our work will be useful for researchers working on music score recognition, and will open up new avenues for research in this field. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Test-Time Augmentation for Document Image Binarization 11th

Test-Time Augmentation for Document Image Binarization

引用

11th Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2023

作者： Rosello, Adrian Castellanos, Francisco J. Martinez-Esteso, Juan P. Gallego, Antonio Javier Calvo-Zaragoza, Jorge Department of Software and Computing Systems University of Alicante Alicante Spain

ISBN: (纸本)9783031366154

Document binarization is a well-known process addressed in the document image analysis literature, which aims to isolate the ink information from the background. Current solutions use deep learning, which requires a great amount of annotated data for training robust models. Data augmentation is known to reduce such annotation requirements, and it can be used in two ways: during training and during prediction. The latter is the so-called Test Time Augmentation (TTA), which has been successfully applied for general classification tasks. In this work, we study the application of TTA for binarization, a more complex and specific task. We focus on cases with a severe scarcity of annotated data over 5 existing binarization benchmarks. Although the results report certain improvements, these are rather limited. This implies that existing TTA strategies are not sufficient for binarization, which points to interesting lines of future work to further boost the performance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Tracking daily paths in home contexts with RSSI fingerprinting based on UWB through deep learning models

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Polo-Rodríguez, A. Valera, J.C. Peral, J. Gil, D. Medina-Quero, J. Department of Computer Engineering Automation and Robotics University of Granada Granada18071 Spain Alicante03690 Spain Department of Software and Computing Systems University of Alicante Alicante03690 Spain

The field of human activity recognition has evolved significantly, driven largely by advancements in Internet of Things (IoT) device technology, particularly in personal devices. This study investigates the use of ultra-wideband (UWB) technology for tracking inhabitant paths in home environments using deep learning models. UWB technology estimates user locations via time-of-flight and time-difference-of-arrival methods, which are significantly affected by the presence of walls and obstacles in real environments, reducing their precision. To address these challenges, we propose a fingerprinting-based approach utilizing received signal strength indicator (RSSI) data collected from inhabitants in two flats (60 m2 and 100 m2) while performing daily activities. We compare the performance of convolutional neural network (CNN), long short-term memory (LSTM), and hybrid CNN+LSTM models, as well as the use of Bluetooth technology. Additionally, we evaluate the impact of the type and duration of the temporal window (future, past, or a combination of both). Our results demonstrate a mean absolute error close to 50 cm, highlighting the superiority of the hybrid model in providing accurate location estimates, thus facilitating its application in daily human activity recognition in residential settings. © The Author(s) 2024.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

Enriching Natural Language Processing systems with Semantic-Pragmatic Information through Communicative Intentions 6

Enriching Natural Language Processing Systems with Semantic-...

引用

6th Doctoral Symposium on Natural Language Processing from the Proyecto ILENIA, PLN-DS 2023

作者： Maestre, María Miró Department of Software and Computing Systems University of Alicante Alicante03690 Spain

Communicative intentions are one of the linguistic elements that usually determine the content of any message we want to express. However, regardless of the high precision Natural Language Processing (NLP) systems are acquiring these days, thanks to the revolution derived from the explosion of the latest large language models (LLMs), these architectures still show a lack of appropriate training in order to detect the intention of a message correctly. For the purpose of improving these systems, the present research project aims to create a communicative intention annotation scheme based on the taxonomy presented in the Speech Act Theory. Such resource could help NLP architectures to consider communicative intentions as a starting point to classify any message depending first on the intention it reflects. With this aim, the scheme will be created with the help of an already annotated corpus in Spanish. Subsequently, we will test the scheme within a classification system so that we can verify the accuracy of the intention patterns detected. In this way, it will be possible to check if NLP systems are capable of identifying Spanish communicative intentions or even generate messages that reflect a given intention, therefore enriching the linguistic information these architectures can infer automatically. © 2021 Copyright for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Syntax Savants-UA at IberLEF 2024: Leveraging FLAN-T5-XXL for Automatic 5W1H Identification in Texts 6

Syntax Savants-UA at IberLEF 2024: Leveraging FLAN-T5-XXL fo...

引用

6th Iberian Languages Evaluation Forum, IberLEF 2024

作者： Grande, Eduardo Begga, Ahmed Department of Software and Computing Systems University of Alicante Spain Department of Computer Science and AI University of Alicante Spain

The 5W1H technique involves formulating six questions to briefly capture the basic information of a news text: What, When, Where, Who, Why, and How. This method enables an easy understanding of the news. This work, part of the FLARES competition at the Iberian Languages Evaluation Forum 2024, presents a Natural Language Processing (NLP) model, specifically FLAN-T5-XXL, designed to automatically extract 5W1H elements with an F1-score of 0.543. Our methodology includes creating task-specific templates and prompts and then fine-tuning the FLAN-T5-XXL model using annotated Spanish news articles provided by the competition organizers. We leverage Low-Rank Adaptation (LoRA) for efficient fine-tuning and conduct comprehensive hyperparameter optimization to enhance model performance and output generation. The evaluation demonstrates that FLAN-T5-XXL significantly outperforms other models. This study underscores the potential of Generative NLP models in automating information extraction from news texts. © 2024 Copyright for this paper by its authors.

关键词： 5W1H Information extraction Large Language Models Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：