检索结果-内蒙古大学图书馆

13th International Conference on natural language processing and Chinese Computing

作者： Liang, Qiuyu Wang, Weihua Yu, Lie Bao, Feilong Inner Mongolia Univ Coll Comp Sci Hohhot Peoples R China Natl & Local Joint Engn Res Ctr Intelligent Infor Hohhot Peoples R China Inner Mongolia Key Lab Multilingual Artificial In Hohhot Peoples R China Natl Univ Def Technol Coll Comp Sci Changsha Peoples R China

ISBN: (纸本)9789819794362;9789819794379

Convolutional Neural Networks (CNNs) have demonstrated effectiveness in knowledge graph embedding, but existing CNN-based methods encounter two main challenges. firstly, CNN-based models with simple architectures are unable to extract latent features. Secondly, these models enhance feature extraction by adding extra modules, which inevitably increases training cost with limited performance improvement. To address these challenges, we go beyond traditional CNNs and propose a novel knowledge graph embedding model, which utilizes the powerful capability of Quaternion Convolutional Neural Networks (QCNNs) for effective representation learning. Specifically, we learn representations of entities and relations in a quaternion space and utilize QCNN to extract the inherent information of the entity-relation matrix. We evaluate the performance of our model on multiple knowledge graph completion benchmark datasets. Experimental results show that our model achieves effective improvements compared to existing CNN-based models. Moreover, in terms of training time, our model is faster than other outstanding models. The code of all experiments is available at https://***/llqy123/ConvQE.

关键词： Quaternion algebra Knowledge graph embedding Link prediction Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning and Retrieval Augmented Generation for Question Answering Using Affordable Large language Models 3

Fine-Tuning and Retrieval Augmented Generation for Question ...

引用

3rd Ukrainian natural language processing workshop, UNLP 2024

作者： Boros, Tiberiu Chivereanu, Radu Dumitrescu, Stefan Daniel Purcaru, Octavian Adobe Systems Bucharest Romania

ISBN: (纸本)9782493814432

We present our proposed system named Sherlock to UNLP 2024 Shared Task on Question Answering winning first place. We employ a mix of methods, from using automatically translated datasets to perform supervised fine-tuning and direct preference optimization on instruction-tuned models, to model weight merging and retrieval augmented generation. We present and motivate our chosen sequence of steps, as well as an ablation study to understand the effect of each additional step. The resulting model and code are made publicly available (download links provided in the paper). © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Evaluating Multilingual language Models for Cross-Lingual ESG Issue Identification 7

Evaluating Multilingual Language Models for Cross-Lingual ES...

引用

Joint workshop of the 7th Financial Technology and natural language processing, 5th Knowledge Discovery from Unstructured Data in Financial Services and 4th Economics and natural language processing, FinNLP-KDF-ECONLP 2024

作者： Li, Wing Yan Chersoni, Emmanuele Ngai, Cindy Sing Bik University of Sussex United Kingdom The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9782493814197

The automation of information extraction from ESG reports has recently become a topic of increasing interest in the natural language processing community. While such information is highly relevant for socially responsible investments, identifying the specific issues discussed in a corporate social responsibility report is one of the first steps in an information extraction pipeline. In this paper, we evaluate methods for tackling the Multilingual Environmental, Social and Governance (ESG) Issue Identification Task. Our experiments use existing datasets in English, French and Chinese with a unified label set. Leveraging multilingual language models, we compare two approaches that are commonly adopted for the given task: off-the-shelf and fine-tuning. We show that fine-tuning models end-to-end is more robust than off-the-shelf methods. Additionally, translating text into the same language has negligible performance benefits. © 2024 ELRA language Resource Association.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Named Entities based on the BERT-BILSTM-ACRF Model Recognition Research 7

Named Entities Based on the BERT-BILSTM-ACRF Model Recogniti...

引用

7th International Conference on natural language processing and Information Retrieval (NLPIR)

作者： Wang, Jingdong Guo, Yongjia Northeast Elect Power Univ Jilin Jilin Peoples R China

ISBN: (纸本)9798400709227

As a crucial first step in the process of constructing knowledge graph, the accuracy of named entity recognition determines the construction effect of the final graph. However, at present, Chinese named entity recognition methods still have many problems, such as long training time and lower accuracy. Hence, we come up with a BERT-BILSTM-ACRF entity recognition method that combines the "self-attention" mechanism. To begin with, Bert model is selected as the embedding layer, the text is vectorized, and the character position in-formation is obtained through the bidirectional Long Short-Term Memory network. Secondly, the internal relationship of the character sequence is further searched through the self-attention mechanism, and finally the final optimal sequence is decoded by the conditional random field model. To check the effectiveness of the BERT-BILSTM-ACRF model, the model is applied to the data set of the university course textbook" Da-ta Structure", and the result reaches 98.97%F1 value and 98.14%accuracy, which has good experimental results and certain practical value.

关键词： Knowledge graph Self-attention mechanism natural language processing Named entity recognition

来源：评论

学校读者我要写书评

暂无评论

Moving from Tabular Knowledge graph Quality Assessment to RDF Triples Leveraging ChatGPT 3

Moving from Tabular Knowledge Graph Quality Assessment to RD...

引用

Joint of the 3rd International workshop One Knowledge graph Generation from Text and Data Quality Meets Machine Learning and Knowledge graphs, TEXT2KG 2024 and DQMLKG 2024

作者： Tuozzo, Gabriele Dipartimento di Informatica Unviersità degli Studi di Salerno SA Fisciano Italy

Data quality assessment is a multifaceted challenge involving various dimensions such as accessibility, interlinking, and completeness. These dimensions are domain-dependent and can be aggregated into a score between 0 and 1, facilitating dataset ranking based on quality. Achieving effective representation and explanation of these rankings poses significant challenges akin to those in machine learning, where interpretability and understandability are crucial. In the domain of natural language processing, data interpretation is a critical yet complex process, often requiring domain expertise and significant resources. Advanced language Model Models (LLMs) offer promise in automating annotation tasks, ensuring consistency, and adapting to specific domains. Leveraging such models for knowledge representation tasks necessitates adept prompt engineering. This study focuses on experiencing state-of-the-art prompt engineering methods, particularly using GPT-3.5, for representing knowledge related to dataset quality. By exploring techniques to extract RDF triples from textual data without predefined labels or constraints, this work aims to enhance interpretability and understanding of dataset quality assessment results while verifying the feasibility on automatic knowledge representation leveraging LLMs. © 2022 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Efficient Aspect-based Summarization of Climate Change Reports with Small language Models 3

Efficient Aspect-Based Summarization of Climate Change Repor...

引用

3rd workshop on NLP for Positive Impact, NLP4PI 2024, held in conjunction with the 2024 Conference on Empirical methods in natural language processing, EMNLP 2024

作者： Ghinassi, Iacopo Catalano, Leonardo Colella, Tommaso Queen Mary University of London London United Kingdom University of Pisa Pisa Italy

ISBN: (纸本)9798891761759

The use of natural language processing (NLP) for helping decision-makers with Climate Change action has recently been highlighted as a use case aligning with a broader drive towards NLP technologies for social good. In this context, Aspect-based Summarization (ABS) systems that extract and summarize relevant information are particularly useful as they provide stakeholders with a convenient way of finding relevant information in expert-curated reports. In this work, we release a new dataset for ABS of Climate Change reports and we employ different Large language Models (LLMs) and so-called Small language Models (SLMs) to tackle this problem in an unsupervised way. Considering the problem at hand, we also show how SLMs are not significantly worse for the problem while leading to reduced carbon footprint;we do so by applying for the first time an existing framework considering both energy efficiency and task performance to the evaluation of zero-shot generative models for ABS. Overall, our results show that modern language models, both big and small, can effectively tackle ABS for Climate Change reports but more research is needed when we frame the problem as a Retrieval Augmented Generation (RAG) problem and our work and dataset will help foster efforts in this direction. © 2024 Association for Computational Linguistics.

关键词： Kyoto Protocol

来源：评论

学校读者我要写书评

暂无评论

A framework for using event evolutionary graphs to rapidly assess the vulnerability of urban flood cascade compound disaster event networks

引用

JOURNAL OF HYDROLOGY 2024年 642卷

作者： Chen, Yilin Zhang, Lidan Chen, Xiaohong Sun Yat sen Univ Sch Civil Engn Zhuhai 519082 Peoples R China Southern Marine Sci & Engn Guangdong Lab Zhuhai Zhuhai 519082 Peoples R China Sun Yat sen Univ Guangdong Engn Technol Res Ctr Water Secur Regulat Guangzhou 510275 Peoples R China Sun Yat sen Univ Guangdong High Educ Inst Key Lab Water Cycle & Water Secur Southern China Guangzhou 510275 Peoples R China

Increasingly frequent flood disasters have caused great losses in recent years. Urban floods induce not only natural geological disasters but also social accidents. These disaster events, called urban flood cascade compound disaster events (UFCCDEs) in this study, have significant cascade, superposition, and amplification effects. However, conventional data sources and processing methods make it difficult to analyze the detailed course of disaster events caused by urban floods, thereby hindering the vulnerability assessment of UFCCDE networks (UFCCDENs). Herein, we propose a framework considering the interactions between disaster events caused by urban floods for rapidly and comprehensively assessing the vulnerability of the UFCCDEN. first, social media data (Sina Weibo) are processed to analyze the spatio-temporal distribution of UFCCDEs and construct a UFCCDEN based on an event evolutionary graph. Second, complex network theory is applied to evaluate the importance of disaster events and the vulnerability of disaster causal chains in the constructed UFCCDEN. Finally, the global efficiency of the network is calculated to assess the propagation efficiency of the UFCCDEN before and after implementing disaster mitigation strategies based on the assessment results to demonstrate the performance of the assessment framework. The coastal megacity Guangzhou was selected as an example. The results showed that, social media data can provide detailed and valid information about UFCCDEs, which can be used to construct the UFCCDEN based on the event evolutionary graph. Waterlogging is found to be the most important disaster event in the UFCCDEN. Furthermore, power facilities, drainage facilities, and roads should be given top priority in the prevention and mitigation of urban floods because of their significant cascading amplification effects. The proposed framework can make the propagation efficiency of the UFCCDEN markedly decrease by 37-62% and 44%, based on the assessment r

关键词： Cascading effects Knowledge graph Social media data Complex network theory Disaster assessment natural language processing

来源：评论

学校读者我要写书评

暂无评论

A Survey on Extracting Knowledge graphs by Employing natural language processing 10

A Survey on Extracting Knowledge Graphs by Employing Natural...

引用

10th International Conference on Web Research, ICWR 2024

作者： Damirchi, Reza Saboohi, Hadi Amini, Amineh Islamic Azad University Karaj Branch Department of Computer Engineering Karaj Iran

ISBN: (纸本)9798350394986

We live in a world of information, and with the ever-increasing rate of content growth, we have no choice but to use machine-based solutions to manage, classify, and use it. However, the produced content is often unstructured, and for computer systems to be able to read and process it, there is no choice but to convert it to structured text. Knowledge graph is one of the ways to represent data in a structured way, and its roots are found in the semantic web. There are different approaches to creating a knowledge graph, but given the significant advances in artificial intelligence, the use of natural language processing is one of the most accurate and automatic ways to do this. In this paper, an attempt has been made to review the latest methods proposed for creating a knowledge graph based on natural language processing. This first allows us to have a better understanding of this research area;in addition, the approaches used by researchers in this field are reviewed and the pros and cons of these approaches are identified. Also, the existing research areas for further work and even the initial ideas for new creative solutions are provided for researchers. © 2024 IEEE.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Towards Building an RDF-based Deep Document Model and Retrieval Augmented Generation System for Enhanced Question Answering with Large language Models

Towards Building an RDF-based Deep Document Model and Retrie...

引用

ISWC 2024 Posters, Demos and Industry Tracks: From Novel Ideas to Industrial Practice, ISWC-Posters-Demos-Industry 2024

作者： Jia, Runsong Zhang, Bowen Rodríguez-Méndez, Sergio J. Omran, Pouya G. Australian National University ACT Canberra2601 Australia QDX Technologies Pte. Ltd. 33A Pagoda Street Singapore059192 Singapore

Knowledge graphs (KGs) are crucial for Retrieval-Augmented Generation (RAG), but traditional methods have limitations in capturing details and querying academic KGs. The challenges lie in identifying the appropriate KG type for RAG, such as a Metadata KG, and optimizing the integration of Large language Models (LLMs) with KGs to enhance retrieval and generation. This paper introduces a novel framework combining the Deep Document Model (DDM) concept and a KG-enhanced Query processing (KGQP) mechanism. DDM provides a comprehensive, hierarchical representation of academic papers using advanced natural language processing (NLP) techniques, while KGQP optimizes complex queries using the KG’s structural information and semantic relationships. The framework also integrates KGs with state-of-the-art LLMs to improve knowledge utilization and downstream task performance. Evaluations show that the KG-based approach surpasses vector-based methods in relevance, accuracy, completeness, and readability. This research demonstrates the potential of combining KGs and LLMs for effective academic knowledge management and discovery. § Submission type: Poster §. © 2024 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Team NLPeers at Chemotimelines 2024: Evaluation of two timeline extraction methods, can generative LLM do it all or is smaller model fine-tuning still relevant ? 6

Team NLPeers at Chemotimelines 2024: Evaluation of two timel...

引用

6th workshop on Clinical natural language processing, ClinicalNLP 2024, held at NAACL 2024

作者： Bannour, Nesrine Andrew, Judith Jeyafreeda Vincent, Marc Université de Paris Imagine Institute Data Science Platform INSERM UMR 1163 ParisF-75015 France Paris France

ISBN: (纸本)9798891761094

This paper presents our two deep learning-based approaches to participate in subtask 1 of the Chemotimelines 2024 Shared task. The first uses a fine-tuning strategy on a relatively small general domain Masked language Model (MLM) model, with additional normalization steps obtained using a simple Large language Model (LLM) prompting technique. The second is an LLM-based approach combining advanced automated prompt search with few-shot in-context learning using the DSPy framework. Our results confirm the continued relevance of the smaller MLM fine-tuned model. It also suggests that the automated few-shot LLM approach can perform close to the fine-tuning-based method without extra LLM normalization and be advantageous under scarce data access conditions. We finally hint at the possibility to choose between lower training examples or lower computing resources requirements when considering both methods. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：