检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Jiacheng Chen, Long School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China

Association as a gift enables people do not have to mention something in completely straightforward words and allows others to understand what they intend to refer to. In this paper, we propose a chain association-based adversarial attack against natural language processing systems, utilizing the comprehension gap between humans and machines. We first generate a chain association graph for Chinese characters based on the association paradigm for building search space of potential adversarial examples. Then, we introduce an discrete particle swarm optimization algorithm to search for the optimal adversarial examples. We conduct comprehensive experiments and show that advanced natural language processing models and applications, including large language models, are vulnerable to our attack, while humans appear good at understanding the perturbed text. We also explore two methods, including adversarial training and associative graph-based recovery, to shield systems from chain association-based attack. Since a few examples that use some derogatory terms, this paper contains materials that may be offensive or upsetting to some people. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multihop Question Answering, A Topological Approach for graph Generation

Multihop Question Answering, A Topological Approach for Grap...

引用

natural language processing (ICNLP), International Conference on

作者： Ramazan Ali Bahrami Rammin Yahyapour Georg-August-Universität Göttingen and GWDG Göttingen Germany

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

One of the frequently used approach for multi-hop question answering (MHQA) is that of graph neural network. In graph neural network based MHQA, learning is primarily based on the graph and connections between nodes of the graph. Creating a meaningful graph from text, however, is a challenging task, and current methods involve extensive data manipulation. In this paper, we propose a novel technique for constructing the mentioned graph. To do so, we first consider paragraphs, sentences, and entities as nodes of the graph. Furthermore, we assume nodes of our graph to be sets of words. Next, in order to find if any given two nodes are connected, we take their intersection, and filter it based on parts of speech types of its elements. If the intersection of the given two nodes is still none-empty after being filtered, an edge is added between them. Our observations show that graphs constructed this way are rich in quantity and variety of connections between nodes, and will result in performance at least equivalent to that of graphs constructed using more complex processes.

关键词： Network topology Spread spectrum communication Data processing Question answering (information retrieval) graph neural networks Question generation Topology

来源：评论

学校读者我要写书评

暂无评论

Selective Attention based graph Convolutional Networks for Aspect-Level Sentiment Classification 15

Selective Attention Based Graph Convolutional Networks for A...

引用

15th workshop on graph-based methods for natural language processing, Textgraphs 2021

作者： Hou, Xiaochen Huang, Jing Wang, Guangtao Qi, Peng He, Xiaodong Zhou, Bowen JD AI Research Mountain ViewCA United States

ISBN: (纸本)9781954085381

Recent work on aspect-level sentiment classification has employed graph Convolutional Networks (GCN) over dependency trees to learn interactions between aspect terms and opinion words. In some cases, the corresponding opinion words for an aspect term cannot be reached within two hops on dependency trees, which requires more GCN layers to model. However, GCNs often achieve the best performance with two layers, and deeper GCNs do not bring any additional gain. Therefore, we design a novel selective attention based GCN model. On one hand, the proposed model enables the direct interaction between aspect terms and context words via the self-attention operation without the distance limitation on dependency trees. On the other hand, a top-k selection procedure is designed to locate opinion words by selecting k context words with the highest attention scores. We conduct experiments on several commonly used benchmark datasets and the results show that our proposed SA-GCN outperforms strong baseline models. © 2021 Association for Computational Linguistics.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PLP 2021: workshop on Programming language processing 21

PLP 2021: Workshop on Programming Language Processing

引用

27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Xu, Chang Ma, Siqi Lo, David Univ Sydney Sydney NSW Australia Univ Queensland Brisbane Qld Australia Singapore Management Univ Singapore Singapore

ISBN: (纸本)9781450383325

The first international workshop on Programming language processing presents interdisciplinary contributions that address programming language procession problems with machine learning and data mining techniques. Recently, there are lots of successful natural language processing methods. But the mining of programming languages could not exactly follow the manner of natural language processing. The difference between natural language and programming language brings in new research challenges and opportunities. The workshop will bring together researchers from machine learning, data mining and software engineering to discuss and debate the path forward for mining the value of programming languages.

关键词： Programming language natural language processing machine learning software engineering data mining

来源：评论

学校读者我要写书评

暂无评论

Learning Clause Representation from Dependency-Anchor graph for Connective Prediction 15

Learning Clause Representation from Dependency-Anchor Graph ...

引用

15th workshop on graph-based methods for natural language processing, Textgraphs 2021

作者： Gao, Yanjun Huang, Ting-Hao Passonneau, Rebecca J. Pennsylvania State University United States

ISBN: (纸本)9781954085381

Semantic representation that supports the choice of an appropriate connective between pairs of clauses inherently addresses discourse coherence, which is important for tasks such as narrative understanding, argumentation, and discourse parsing. We propose a novel clause embedding method that applies graph learning to a data structure we refer to as a dependencyanchor graph. The dependency anchor graph incorporates two kinds of syntactic information, constituency structure and dependency relations, to highlight the subject and verb phrase relation. This enhances coherencerelated aspects of representation. We design a neural model to learn a semantic representation for clauses from graph convolution over latent representations of the subject and verb phrase. We evaluate our method on two new datasets: a subset of a large corpus where the source texts are published novels, and a new dataset collected from students' essays. The results demonstrate a significant improvement over tree-based models, confirming the importance of emphasizing the subject and verb phrase. The performance gap between the two datasets illustrates the challenges of analyzing student's written text, plus a potential evaluation task for coherence modeling and an application for suggesting revisions to students. © 2021 Association for Computational Linguistics.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Improving Query graph Generation for Complex Question Answering over Knowledge Base

Improving Query Graph Generation for Complex Question Answer...

引用

2021 Conference on Empirical methods in natural language processing, EMNLP 2021

作者： Qin, Kechen Li, Cheng Pavlu, Virgil Aslam, Javed A. Khoury College of Computer Sciences Northeastern University United States CodaMetrix

ISBN: (纸本)9781955917094

Most of the existing Knowledge-based Question Answering (KBQA) methods first learn to map the given question to a query graph, and then convert the graph to an executable query to find the answer. The query graph is typically expanded progressively from the topic entity based on a sequence prediction model. In this paper, we propose a new solution to query graph generation that works in the opposite manner: we start with the entire knowledge base and gradually shrink it to the desired query graph. This approach improves both the efficiency and the accuracy of query graph generation, especially for complex multi-hop questions. Experimental results show that our method achieves state-of-the-art performance on ComplexWebQuestion (CWQ) dataset. © 2021 Association for Computational Linguistics

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Building term hierarchies using graph-based clustering 6

Building term hierarchies using graph-based clustering

引用

6th International Conference on natural language processing and Information Retrieval, NLPIR 2022

作者： Hloch, Mark Van Meegen, Markus Kubek, Mario Unger, Herwig Faculty of Electrical Engineering and Computer Science Hochschule Niederrhein - University of Applied Sciences Krefeld Germany Department of Computer Science Georgia State University Atlanta United States Fern Universität Hagen Chair of Computer Engineering Hagen Germany

ISBN: (纸本)9781450397629

Classical tasks of a librarian, such as screening and categorizing new documents based on their content, are increasingly replaced by search engines or through the use of cataloging software. A first overview of a corpus topical orientation can be achieved by combining graph-based search engines and clustering methods. Existing classical clustering methods, however, often require an a priori specification of the desired number of clusters to be output and do not consider term relationships in graphs, which is deficient from a practical point of view. Therefore, fully unsupervised graph-based clustering approaches at the term level offer new possibilities that mitigate these shortcomings. Within this work, a set of novel graph-based clustering algorithms have been developed. The hierarchical clustering algorithm (HCA) forms term hierarchies by iteratively isolating nodes of a given co-occurrence graph based on the evaluation of the edge weight between the nodes. based on the co-occurrence graph inherent relationships of terms, a new graph is built agglomerative forming individual term clusters of related terms. The feasibility of the outlined methods for text analysis is shown. © 2022 ACM.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

A Bidirectional Tree Tagging Scheme for Joint Medical Relation Extraction

A Bidirectional Tree Tagging Scheme for Joint Medical Relati...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Luo, Xukun Liu, Weijie Ma, Meng Wang, Ping Peking Univ Beijing Peoples R China

ISBN: (纸本)9781665488679

Joint medical relation extraction refers to extracting triples, composed of entities and relations, from the medical text with a single model. One of the solutions is to convert this task into a sequential tagging task. However, in the existing works, the methods of representing and tagging the triples in a linear way failed to the overlapping triples, and the methods of organizing the triples as a graph faced the challenge of large computational effort. In this paper, inspired by the tree-like relation structures in the medical text, we propose a novel scheme called Bidirectional Tree Tagging (BiTT) to form the medical relation triples into two binary trees and convert the trees into a word-level tags sequence. based on BiTT scheme, we develop a joint relation extraction model to predict the BiTT tags and further extract medical triples efficiently. Our model outperforms the best baselines by 2.0% and 2.5% in F1 score on two medical datasets. What's more, the models with our BiTT scheme also obtain promising results in three public datasets of other domains.

关键词： medical information systems text analysis natural language processing

来源：评论

学校读者我要写书评

暂无评论

Learning Inter-Entity Interaction for Few-Shot Knowledge graph Completion

Learning Inter-Entity Interaction for Few-Shot Knowledge Gra...

引用

2022 Conference on Empirical methods in natural language processing, EMNLP 2022

作者： Li, Yuling Yu, Kui Huang, Xiaoling Zhang, Yuhong Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei China School of Computer Science and Information Enginerring Hefei University of Technology China

Few-shot knowledge graph completion (FKGC) aims to infer unknown fact triples of a relation using its few-shot reference entity pairs. Recent FKGC studies focus on learning semantic representations of entity pairs by separately encoding the neighborhoods of head and tail entities. Such practice, however, ignores the inter-entity interaction, resulting in low-discrimination representations for entity pairs, especially when these entity pairs are associated with 1-to-N, N-to-1, and N-to-N relations. To address this issue, this paper proposes a novel FKGC model, named Cross-Interaction Attention Network (CIAN) to investigate the inter-entity interaction between head and tail entities. Specifically, we first explore the interactions within entities by computing the attention between the task relation and each entity neighbor, and then model the interactions between head and tail entities by letting an entity to attend to the neighborhood of its paired entity. In this way, CIAN can figure out the relevant semantics between head and tail entities, thereby generating more discriminative representations for entity pairs. Extensive experiments on two public datasets show that CIAN outperforms several state-of-the-art methods. The source code is available at https://***/cjlyl/FKGC-CIAN. © 2022 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Strategies for the Analysis of Large Social Media Corpora: Sampling and Keyword Extraction methods

引用

CORPUS PRAGMATICS 2023年第3期7卷 241-265页

作者： Moreno-Ortiz, Antonio Garcia-Gamez, Maria Univ Malaga Dept English French & German Philol Malaga Spain

In the context of the COVID-19 pandemic, social media platforms such as Twitter have been of great importance for users to exchange news, ideas, and perceptions. Researchers from fields such as discourse analysis and the social sciences have resorted to this content to explore public opinion and stance on this topic, and they have tried to gather information through the compilation of large-scale corpora. However, the size of such corpora is both an advantage and a drawback, as simple text retrieval techniques and tools may prove to be impractical or altogether incapable of handling such masses of data. This study provides methodological and practical cues on how to manage the contents of a large-scale social media corpus such as Chen et al. (JMIR Public Health Surveill 6(2):e19273, 2020) COVID-19 corpus. We compare and evaluate, in terms of efficiency and efficacy, available methods to handle such a large corpus. first, we compare different sample sizes to assess whether it is possible to achieve similar results despite the size difference and evaluate sampling methods following a specific data management approach to storing the original corpus. Second, we examine two keyword extraction methodologies commonly used to obtain a compact representation of the main subject and topics of a text: the traditional method used in corpus linguistics, which compares word frequencies using a reference corpus, and graph-based techniques as developed in natural language processing tasks. The methods and strategies discussed in this study enable valuable quantitative and qualitative analyses of an otherwise intractable mass of social media data.

关键词： Covid-19 language Large-scale social media corpus Sampling methods Sampling sizes Keyword extraction

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：