检索结果-内蒙古大学图书馆

10th Annual International Scientific and Practical Conference named after A. I. Kitov Information Technologies and Mathematical methods in Economics and Management, IT and MM 2020

作者： Gurin, Anatoly A. Plekhanov Russian University of Economics 36 Stremyanny lane Moscow115998 Russia

Semantic analysis has great potential applications in various fields of science and the national economy. Much of the information in the world is not structured, so there is the problem of processing and extracting useful data. natural language processing is a very complex process. On November 23, 2017, as part of the 2017 Runet Prize award ceremony, the HOT-LIST 2018 was presented, that identified the main digital trends of 2018 and presented a list of trendsetters in 10 technology, innovation and business *** were included 10 leading companies in 10 areas and the first area is AI technologies. AI technology has become a key technology trend in 2018, and the volume of global investment in these technologies and products based on them in excess of $ 1 billion.[25] More than 180 private companies working on projects in the field of AI technologies have been purchased during the period 2011-2018. According to IDC Customer Insights & Analysis.[25] During the period 2011-2018 it was purchased more than 180 private companies working on projects of AI technologies. According to forecasts of Frost & Sullivan, by 2022 artificial intelligence market will grow to $ 10 billion using machine learning technologies and natural language recognition in advertising, retail, finance and health.[25]. © 2021 Copyright for this paper by its authors.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Constructing a Knowledge graph for Vietnamese Legal Cases with Heterogeneous graphs

arXiv

引用

arXiv 2023年

作者： Vuong, Thi-Hai-Yen Hoang, Minh-Quan Nguyen, Tan-Minh Nguyen, Hoang-Trung Nguyen, Ha-Thanh VNU University of Engineering and Technology Hanoi Viet Nam National Institute of Informatics Tokyo Japan

This paper presents a knowledge graph construction method for legal case documents and related laws, aiming to organize legal information efficiently and enhance various downstream tasks. Our approach consists of three main steps: data crawling, information extraction, and knowledge graph deployment. first, the data crawler collects a large corpus of legal case documents and related laws from various sources, providing a rich database for further processing. Next, the information extraction step employs natural language processing techniques to extract entities such as courts, cases, domains, and laws, as well as their relationships from the unstructured text. Finally, the knowledge graph is deployed, connecting these entities based on their extracted relationships, creating a heterogeneous graph that effectively represents legal information and caters to users such as lawyers, judges, and scholars. The established baseline model leverages unsupervised learning methods, and by incorporating the knowledge graph, it demonstrates the ability to identify relevant laws for a given legal case. This approach opens up opportunities for various applications in the legal domain, such as legal case analysis, legal recommendation, and decision support. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

E2E-VLP: End-to-End Vision-language Pre-training Enhanced by Visual Learning 59

E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by...

引用

Joint Conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th International Joint Conference on natural language processing (IJCNLP) / 6th workshop on Representation Learning for NLP (RepL4NLP)

作者： Xu, Haiyang Yan, Ming Li, Chenliang Bi, Bin Huang, Songfang Xiao, Wenming Huang, Fei Alibaba Grp Hangzhou Peoples R China

ISBN: (纸本)9781954085527

Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-stage pipeline. In this paper, we propose the first end-to-end vision-language pre-trained model for both V+L understanding and generation, namely E2E-VLP, where we build a unified Transformer framework to jointly learn visual representation, and semantic alignments between image and text. We incorporate the tasks of object detection and image captioning into pre-training with a unified Transformer encoder-decoder architecture for enhancing visual learning. An extensive set of experiments have been conducted on well-established vision-language downstream tasks to demonstrate the effectiveness of this novel VLP paradigm.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Joint Learning of the graph and the Data Representation for graph-based Semi-Supervised Learning 14

Joint Learning of the Graph and the Data Representation for ...

引用

14th workshop on graph-based methods for natural language processing, Textgraphs 2020, in conjunction with the 28th International Conference on Computational Linguistics, COLING 2020

作者： Vargas-Vieyra, Mariana Bellet, Aurélien Denis, Pascal Magnet Team Inria Lille - Nord Europe France Université de Lille CNRS UMR 9189 CRIStAL Villeneuve d’Ascq59650 France

ISBN: (纸本)9781952148422

graph-based semi-supervised learning is appealing when labels are scarce but large amounts of unlabeled data are available. These methods typically use a heuristic strategy to construct the graph based on some fixed data representation, independently of the available labels. In this paper, we propose to jointly learn a data representation and a graph from both labeled and unlabeled data such that (i) the learned representation indirectly encodes the label information injected into the graph, and (ii) the graph provides a smooth topology with respect to the transformed data. Plugging the resulting graph and representation into existing graph-based semi-supervised learning algorithms like label spreading and graph convolutional networks, we show that our approach outperforms standard graph construction methods on both synthetic data and real datasets. © COLING *** rights reserved.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Detection of cyberbullying in Arabic social media using dynamic graph neural network

Detection of cyberbullying in Arabic social media using dyna...

引用

2022 Tunisian-Algerian Joint Conference on Applied Computing, TACC 2022

作者： Bouliche, Ahmed Rezoug, Abdellah Department of computer science Faculty of sciences University of Boumerdes Boumerdes Algeria

Despite all the advantages social networks have brought to the world, they are also a very favourable environment for the growth of so-called electronic crimes. Textual exchanges between users may include clues to crimes committed or being prepared. Usually, methods of natural language processing (NLP) and neural networks are effective ways to detect cybercrimes particularly cyberbullying. In this paper, we proposed techniques that allow to use structures of dynamic temporal graphs as direct inputs to a model without turning them into static graphs as well as a message passing algorithm that fits well with the approach. The effectiveness of these techniques was tested on a prototype model. Fortunately, the proposed techniques have been proven to work, but with poor model performance. The applicability of a crime detector can be established with a session classifier if the data is more general, i.e., represents all the language used by bullies. © 2022 Copyright for this paper by its authors.

关键词： Computer crime

来源：评论

学校读者我要写书评

暂无评论

Amendable Generation for Dialogue State Tracking 3

Amendable Generation for Dialogue State Tracking

引用

3rd workshop on natural language processing for Conversational AI, NLP4ConvAI 2021

作者： Tian, Xin Huang, Liankai Lin, Yingzhan Bao, Siqi He, Huang Yang, Yunyi Wu, Hua Wang, Fan Sun, Shuqi Baidu Inc. China

ISBN: (纸本)9781954085862

In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current turn are prone to be carried over to the next turn, causing error propagation. In this paper, we propose a novel Amendable Generation for Dialogue State Tracking (AG-DST), which contains a two-pass generation process: (1) generating a primitive dialogue state based on the dialogue of the current turn and the previous dialogue state, and (2) amending the primitive dialogue state from the first pass. With the additional amending generation pass, our model is tasked to learn more robust dialogue state tracking by amending the errors that still exist in the primitive dialogue state, which plays the role of reviser in the double-checking process and alleviates unnecessary error propagation. Experimental results show that AG-DST significantly outperforms previous works in two active DST datasets (MultiWOZ 2.2 and WOZ 2.0), achieving new state-of-the-art performances. © 2021 Association for Computational Linguistics.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Large language Models on graphs: A Comprehensive Survey

arXiv

引用

arXiv 2023年

作者： Jin, Bowen Liu, Gang Han, Chi Jiang, Meng Ji, Heng Han, Jiawei University of Illinois at Urbana-Champaign United States University of Notre Dame United States

Large language models (LLMs), such as GPT4 and LLaMA, are creating significant advancements in natural language processing, due to their strong text encoding/decoding ability and newly found emergent capability (e.g., reasoning). While LLMs are mainly designed to process pure texts, there are many real-world scenarios where text data is associated with rich structure information in the form of graphs (e.g., academic networks, and e-commerce networks) or scenarios where graph data is paired with rich textual information (e.g., molecules with descriptions). Besides, although LLMs have shown their pure text-based reasoning ability, it is underexplored whether such ability can be generalized to graphs (i.e., graph-based reasoning). In this paper, we provide a systematic review of scenarios and techniques related to large language models on graphs. We first summarize potential scenarios of adopting LLMs on graphs into three categories, namely pure graphs, text-attributed graphs, and text-paired graphs. We then discuss detailed techniques for utilizing LLMs on graphs, including LLM as Predictor, LLM as Encoder, and LLM as Aligner, and compare the advantages and disadvantages of different schools of models. Furthermore, we discuss the real-world applications of such methods and summarize open-source codes and benchmark datasets. Finally, we conclude with potential future research directions in this fast-growing field. The related source can be found at https://***/PeterGriffinJin/Awesome-language-Model-on-graphs. Copyright © 2023, The Authors. All rights reserved.

关键词： graph neural networks

来源：评论

学校读者我要写书评

暂无评论

graph Representation Learning in Document Wikification 16th

Graph Representation Learning in Document Wikification

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Saeidi, Mozhgan Milios, Evangelos Zeh, Norbert Dalhousie Univ Halifax NS Canada

ISBN: (纸本)9783030861599;9783030861582

Wikification (entity annotation) is a challenging task in natural language processing (NLP). It is a method to automatically enrich a text with links to Wikipedia as a knowledge base. Wikification starts from detecting ambiguous mentions in the document, and later tries to disambiguate those mentions. In the core of the Wikification task, there is one other important NLP task: word representation. This paper proposes a new word representation for senses of a mention with graph convolutional networks architecture. Senses are the possible meanings of one mention, based on the knowledge base. In our representation modeling, we used the context document and the first paragraph of each Wikipedia page to enhance our contextual representation. Using the nearest neighbor algorithm for disambiguating the mentions via our sense representations, we show the efficiency of our representations. The results of comparing our method with recent state-of-the-art methods show the efficiency of our solution.

关键词： Representation learning graph convolutional networks Wikification Document ambiguity

来源：评论

学校读者我要写书评

暂无评论

graph Relational Topic Model with Higher-order graph Attention Auto-encoders

Graph Relational Topic Model with Higher-order Graph Attenti...

引用

作者： Xie, Qianqian Huang, Jimin Du, Pan Peng, Min Univ Manchester Dept Comp Sci Manchester Lancs England Wuhan Univ Sch Comp Sci Wuhan Peoples R China Univ Montreal Dept Comp Sci & Operat Res Montreal PQ Canada

ISBN: (纸本)9781954085541

Learning low-dimensional representations of networked documents is a crucial task for documents linked in network structures. Relational Topic Models (RTMs) have shown their strengths in modeling both document contents and relations to discover the latent topic semantic representations. However, higher-order correlation structure information among documents is largely ignored in these methods. Therefore, we propose a novel graph relational topic model (GRTM) for document network, to fully explore and mix neighborhood information of documents on each order, based on the Higher-order graph Attention Network (HGAT) with the log-normal prior in the graph attention. The proposed method can address the aforementioned issue via the information propagation among document-document based on the HGAT probabilistic encoder, to learn efficient networked document representations in the latent topic space, which can fully reflect document contents, along with document connections. Experiments on several real-world document network datasets show that, through fully exploring information in documents and document networks, our model achieves better performance on unsupervised representation learning and outperforms existing competitive methods in various downstream tasks.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

graph-based Syntactic Word Embeddings 14

Graph-based Syntactic Word Embeddings

引用

14th workshop on graph-based methods for natural language processing, Textgraphs 2020, in conjunction with the 28th International Conference on Computational Linguistics, COLING 2020

作者： Al-Ghezi, Ragheb Kurimo, Mikko Aalto University Finland

ISBN: (纸本)9781952148422

We propose a simple and efficient framework to learn syntactic embeddings based on information derived from constituency parse trees. Using biased random walk methods, our embeddings not only encode syntactic information about words, but they also capture contextual information. We also propose a method to train the embeddings on multiple constituency parse trees to ensure the encoding of global syntactic representation. Quantitative evaluation of the embeddings shows competitive performance on POS tagging task when compared to other types of embeddings, and qualitative evaluation reveals interesting facts about the syntactic typology learned by these embeddings. © COLING *** rights reserved.

关键词： Embeddings

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：