检索结果-内蒙古大学图书馆

IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS)

作者： Alberto Roberto Marinelli Antonio Carta Lucia C. Passaro dept. of Computer Science University of Pisa Pisa Italy

ISBN: (数字)9798350366235

ISBN: (纸本)9798350366242

natural language processing (NLP) has witnessed a paradigm shift with Large language Models (LLMs), yet the static knowledge from pre-training can lead to knowledge obsolescence. This study focuses on the dynamic relationship between LLMs and evolving knowledge, using GPT-2 as a case study. Leveraging an existing framework, we update models with monthly Wikipedia dumps and Wikidata probes, addressing the stability-plasticity trade-off. We introduce a novel synthetic data generation method for experimental control and present SMARTREVIEW, a state-of-the-art continual learning method. This work advances understanding and methodologies in tackling knowledge obsolescence in evolving language models.

关键词： Continuing education Training Process control Aging natural language processing Stability analysis Online services

来源：评论

学校读者我要写书评

暂无评论

Classification of Software Engineering Contributions to Support Validation Techniques and Research Applications 22

Classification of Software Engineering Contributions to Supp...

引用

26th ACM International conference on Evaluation and Assessment in Software Engineering, EASE 2022

作者： Kaplan, Angelika Karlsruhe Institute of Technology Germany

ISBN: (纸本)9781450396134

Science and thereby software engineering (SE) research enables progress and innovation. SE research has high economic relevance and serves as an enabler for innovations in other research fields as well. Researchers in this field perform many activities and face corresponding challenges. They have to design and conduct research, while deciding on an appropriate method design for a scientific or practical problem. They have to review research while critically assessing research outcomes in a systematic and comparable way. They have to search for research outcomes to find research gaps to build upon. Likewise, by finding related information, they are able to justify relevance of own research work. These searching processes are done via keyword-based searches while struggling with information overload due to immensely growing number of SE papers published every year. Thus, there is the need for conceptual approaches, automated mechanisms, and a rethinking about scholarly communication to support these research activities and challenges in an effective, efficient, and comprehensible way. There are a variety of available classifications for research methods in literature. Additionally, empirical standards for research methods are continuously developed and adapted from other research fields. However, there is no consistency in the covered research methods, nor in the used terminology as well as no systematic approach to structure this body of research knowledge (e.g., template research questions, research methods, validity threats, replication types). Therefore, this doctoral thesis will provide a unified classification scheme to describe the characteristics of SE research. This further enables classification of SE papers and a corresponding queryable knowledge management system and, thus, advance state of practice. © 2022 ACM.

关键词： natural language processing meta-research in software engineering machine learning knowledge management system empirical software engineering research

来源：评论

学校读者我要写书评

暂无评论

OnNER: An Ontology for Semantic Representation of Named Entities in Scholarly Publications 14

OnNER: An Ontology for Semantic Representation of Named Enti...

引用

14th International conference on Formal Ontology in Information Systems, FOIS 2024

作者： Reza, Umayer Zhang, Xuelian Hahmann, Torsten School of Computing and Information Science University of Maine United States

ISBN: (纸本)9781643685618

A significant portion of scientific knowledge resides within scholarly publications, both in print and digital formats. Recent advancements in natural language processing and information extraction techniques have enhanced the accessibility of this knowledge for further automated querying and processing. Structured and semantically-aware representations, such as ontologies, play a crucial role in simplifying and integrating access to this vast pool of knowledge. While several ontologies have been developed to capture the structure and discourse of scientific publications, there is a notable scarcity of ontologies for succinctly representing named entities that are present in scholarly documents. This paper introduces the Ontology for Named Entity Representation (OnNER) to address this gap. OnNER is designed to represent named entities - the terms identified and labeled using named entity recognition (NER) methods - from scholarly publications. The ontology provides a structured semantic representation of the named entities, how they are labeled, and where they occur. We discuss the overall design of OnNER, its integration with other ontologies, and demonstrate how the ontology facilitates advanced querying of named entities’ presence and collocation within and across publications. © 2024 The Authors.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-language Representations and Class Center Learning 24

TagOOD: A Novel Approach to Out-of-Distribution Detection vi...

引用

32nd ACM International conference on Multimedia, MM 2024

作者： Li, Jinglun Zhou, Xinyu Jiang, Kaixun Hong, Lingyi Guo, Pinxue Chen, Zhaoyu Ge, Weifeng Zhang, Wenqiang Shanghai Engineering Research Center of Ai & Robotics Academy for Engineering & Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Engineering Research Center of Ai & Robotics Ministry of Education Academy for Engineering & Technology Fudan University China

ISBN: (纸本)9798400706868

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose TagOOD, a novel approach for OOD detection that leverages vision language representations to achieve label-free object feature decoupling from whole images. This decomposition enables a more focused analysis of object semantics, enhancing OOD detection performance. Subsequently, TagOOD trains a lightweight network on the extracted object features to learn representative class centers. These centers capture the central tendencies of IND object classes, minimizing the influence of irrelevant image features during OOD detection. Finally, our approach efficiently detects OOD samples by calculating distance-based metrics as OOD scores between learned centers and test samples. We conduct extensive experiments to evaluate TagOOD on several benchmark datasets and demonstrate its superior performance compared to existing OOD detection methods. This work presents a novel perspective for further exploration of multimodal information utilization in OOD detection, with potential applications across various tasks. Code is available at: https://***/Jarvisgivemeasuit/tagood. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

empirical analysis of binding precedent efficiency in Brazilian Supreme Court via case classification

引用

ARTIFICIAL INTELLIGENCE AND LAW 2025年

作者： Tinarrage, Raphael Ennes, Henrique Resck, Lucas Gomes, Lucas T. Ponciano, Jean R. Poco, Jorge Fundacao Getulio Vargas EMAp Rio De Janeiro Brazil Fundacao Getulio Vargas Direito Rio Rio De Janeiro Brazil Univ Sao Paulo ICMC Sao Carlos Brazil Univ Cote Azur INRIA Valbonne France IST Austria Klosterneuburg Austria

Binding precedents (s & uacute;mulas vinculantes) constitute a juridical instrument unique to the Brazilian legal system and whose objectives include the protection of the Federal Supreme Court against repetitive demands. Studies of the effectiveness of these instruments in decreasing the Court's exposure to similar cases, however, indicate that they tend to fail in such a direction, with some of the binding precedents seemingly creating new demands. We empirically assess the legal impact of five binding precedents, 11, 14, 17, 26, and 37, at the highest Court level through their effects on the legal subjects they address. This analysis is only possible through the comparison of the Court's ruling about the precedents' themes before they are created, which means that these decisions should be detected through techniques of Similar Case Retrieval, which we tackle from the angle of Case Classification. The contributions of this article are therefore twofold: on the mathematical side, we compare the use of different methods of natural language processing - TF-IDF, LSTM, Longformer, and regex - for Case Classification, whereas on the legal side, we contrast the inefficiency of these binding precedents with a set of hypotheses that may justify their repeated usage. We observe that the TF-IDF models performed slightly better than LSTM and Longformer when compared through common metrics;however, the deep learning models were able to detect certain important legal events that TF-IDF missed. On the legal side, we argue that the reasons for binding precedents to fail in responding to repetitive demand are heterogeneous and case-dependent, making it impossible to single out a specific cause. We identify five main hypotheses, which are found in different combinations in each of the precedents studied.

关键词： Case classification Similar case retrieval Binding precedents Judicial efficiency Brazilian supreme court

来源：评论

学校读者我要写书评

暂无评论

Role of language Relatedness in Multilingual Fine-tuning of language Models: A Case Study in Indo-Aryan languages

Role of Language Relatedness in Multilingual Fine-tuning of ...

引用

2021 conference on empirical methods in natural language processing, EMNLP 2021

作者： Dhamecha, Tejas Indulal Rudra Murthy, V. Bharadwaj, Samarth Sankaranarayanan, Karthik Bhattacharyya, Pushpak IBM Research India Department of Computer Science and Engineering IIT Bombay India

ISBN: (纸本)9781955917094

We explore the impact of leveraging the relatedness of languages that belong to the same family in NLP models using multilingual fine-tuning. We hypothesize and validate that multilingual fine-tuning of pre-trained language models can yield better performance on downstream NLP applications, compared to models fine-tuned on individual languages. A first of its kind detailed study is presented to track performance change as languages are added to a base language in a graded and greedy (in the sense of best boost of performance) manner;which reveals that careful selection of subset of related languages can significantly improve performance than utilizing all related languages. The Indo-Aryan (IA) language family is chosen for the study, the exact languages being Bengali, Gujarati, Hindi, Marathi, Oriya, Punjabi and Urdu. The script barrier is crossed by simple rule-based transliteration of the text of all languages to Devanagari. Experiments are performed on mBERT, IndicBERT, MuRIL and two RoBERTa-based LMs, the last two being pre-trained by us. Low resource languages, such as Oriya and Punjabi, are found to be the largest beneficiaries of multilingual fine-tuning. Textual Entailment, Entity Classification, Section Title Prediction, tasks of IndicGLUE and POS tagging form our test bed. Compared to monolingual fine tuning we get relative performance improvement of up to 150% in the downstream tasks. The surprise take-away is that for any language there is a particular combination of other languages which yields the best performance, and any additional language is in fact detrimental. © 2021 Association for Computational Linguistics

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Large language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning 38

Large Language Models-guided Dynamic Adaptation for Temporal...

引用

38th conference on Neural Information processing Systems, NeurIPS 2024

作者： Wang, Jiapu Sun, Kai Luo, Linhao Wei, Wei Hu, Yongli Liew, Alan Wee-Chung Pan, Shirui Yin, Baocai Beijing University of Technology China Monash University Australia University of Hong Kong Hong Kong Griffith University Australia

Temporal Knowledge Graph Reasoning (TKGR) is the process of utilizing temporal information to capture complex relations within a Temporal Knowledge Graph (TKG) to infer new knowledge. Conventional methods in TKGR typically depend on deep learning algorithms or temporal logical rules. However, deep learning-based TKGRs often lack interpretability, whereas rule-based TKGRs struggle to effectively learn temporal rules that capture temporal patterns. Recently, Large language Models (LLMs) have demonstrated extensive knowledge and remarkable proficiency in temporal reasoning. Consequently, the employment of LLMs for Temporal Knowledge Graph Reasoning (TKGR) has sparked increasing interest among researchers. Nonetheless, LLMs are known to function as black boxes, making it challenging to comprehend their reasoning process. Additionally, due to the resource-intensive nature of fine-tuning, promptly updating LLMs to integrate evolving knowledge within TKGs for reasoning is impractical. To address these challenges, in this paper, we propose a Large language Models-guided Dynamic Adaptation (LLM-DA) method for reasoning on TKGs. Specifically, LLM-DA harnesses the capabilities of LLMs to analyze historical data and extract temporal logical rules. These rules unveil temporal patterns and facilitate interpretable reasoning. To account for the evolving nature of TKGs, a dynamic adaptation strategy is proposed to update the LLM-generated rules with the latest events. This ensures that the extracted rules always incorporate the most recent knowledge and better generalize to the predictions on future events. Experimental results show that without the need of fine-tuning, LLM-DA significantly improves the accuracy of reasoning over several common datasets, providing a robust framework for TKGR tasks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Applying natural language processing in Healthcare Using Data Science

Applying Natural Language Processing in Healthcare Using Dat...

引用

International conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions)

作者： Smriti Sett Ajay Vikram Singh Amity Institute of Information Technology Amity University Noida India

ISBN: (数字)9798350350357

ISBN: (纸本)9798350350364

This research paper explores how advancements in Artificial Intelligence, particularly natural language processing (NLP), are impacting healthcare. NLP, which can analyse and understand human language, is being integrated into clinical research. The importance of integrating natural language processing (NLP) methods into clinical informatics research has been increasingly acknowledged in recent years, leading to significant advancements. NLP systems are designed to process medical documents, sentences, and individual words to extract valuable information. Clinical text classification with filtering tools, techniques and domain knowledge improves accuracy on imbalanced and noisy data. This review analyses existing studies on NLP in healthcare, exploring different approaches and technical aspects. The paper also highlights the use of NLP in various healthcare applications and identifies areas for future research to further develop NLP-driven smart healthcare.

关键词： Social networking (online) Reviews Text categorization Medical services Data science Market research natural language processing

来源：评论

学校读者我要写书评

暂无评论

Towards Leveraging Semantic Web Technologies for Automated UI Element Annotation

Towards Leveraging Semantic Web Technologies for Automated U...

引用

International conference on Inventive Computation Technologies (ICICT)

作者： Trisanth Srinivasan Cyrion Labs

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

This paper presents a novel Chrome extension for automated web UI element annotation using Semantic Web technologies. The primary objective is to enable Visual language Models (VLMs) and Large language Models (LLMs) to quickly comprehend and interact with the web by transforming unstructured visual data into structured semantic information. Our approach integrates natural language processing, vector embeddings, and FAISS for real-time similarity search. In addition to detailing the system architecture and implementation, we propose a custom algorithm for semantic annotation and provide a comparison with traditional methods. Evaluations via BLEU scores and search time measurements demonstrate the extension's efficiency.

关键词： Semantic Web Visualization Annotations Large language models Semantics Systems architecture Real-time systems natural language processing Vectors Time measurement

来源：评论

学校读者我要写书评

暂无评论

Persian Stance Detection with Transfer Learning and Data Augmentation 27

Persian Stance Detection with Transfer Learning and Data Aug...

引用

27th International Computer conference, Computer Society of Iran, CSICC 2022

作者： Nasiri, Homa Analoui, Morteza Iran University Of Science And Technology Dept. Computer Engineering Tehran Iran

ISBN: (纸本)9781665480277

With increasing public access to social media, many dubious and inaccurate content is being generated and shared for profitable targets. This content is generated to attract audiences, increase revenue, impact people's decisions, and influence important events such as political elections. Manually, detecting this news is very time-consuming, costly, and tedious, so the automatic detection of this content has attracted the attention of many natural language processing researchers. In this research, we have investigated the effect of using EDA data augmentation methods and the ParsBERT pre-training model to solve the problem of scarcity and lack of annotated datasets in the Persian stance detection task The results of this study indicate that we can identify the stance of news to the specific claim better than previous works with the help of data augmentation methods, content-based representation of the data, and the ParsBERT model. © 2022 IEEE.

关键词： Social networking (online) Computational modeling Voting Transfer learning Data models natural language processing Task analysis

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：