检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Ansarinia, Morteza Schrater, Paul Cardoso-Leite, Pedro University of Luxembourg Department of Behavioural and Cognitive Sciences Luxembourg University of Minnesota Twin Cities Depts. of Computer Science and Psychology United States

Traditionally, theory and practice of Cognitive Control are linked via literature reviews by human domain experts. This approach, however, is inadequate to track the ever-growing literature. It may also be biased, and yield redundancies and confusion. Here we present an alternative approach. We performed automated text analyses on a large body of scientific texts to create a joint representation of tasks and constructs. More specifically, 385,705 scientific abstracts were first mapped into an embedding space using a transformers-based language model. Document embeddings were then used to identify a task-construct graph embedding that grounds constructs on tasks and supports nuanced meaning of the constructs by taking advantage of constrained random walks in the graph. This joint task-construct graph embedding, can be queried to generate task batteries targeting specific constructs, may reveal knowledge gaps in the literature, and inspire new tasks and novel hypotheses. © 2022, CC BY.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

Graph Convolutions over Constituent Trees for Syntax-Aware S...

引用

Conference on Empirical methods in natural language processing (EMNLP)

作者： Marcheggiani, Diego Titov, Ivan Amazon North Seattle WA USA Univ Edinburgh Sch Informat ILCC Edinburgh Scotland Univ Amsterdam ILLC Amsterdam Netherlands

ISBN: (纸本)9781952148606

Semantic role labeling (SRL) is the task of identifying predicates and labeling argument spans with semantic roles. Even though most semantic-role formalisms are built upon constituent syntax, and only syntactic constituents can be labeled as arguments (e.g., FrameNet and PropBank), all the recent work on syntax-aware SRL relies on dependency representations of syntax. In contrast, we show how graph convolutional networks (GCNs) can be used to encode constituent structures and inform an SRL system. Nodes in our SpanGCN correspond to constituents. The computation is done in 3 stages. first, initial node representations are produced by 'composing' word representations of the first and last words in the constituent. Second, graph convolutions relying on the constituent tree are performed, yielding syntactically-informed constituent representations. Finally, the constituent representations are 'decomposed' back into word representations, which are used as input to the SRL classifier. We evaluate SpanGCN against alternatives, including a model using GCNs over dependency trees, and show its effectiveness on standard English SRL benchmarks CoNLL-2005, CoNLL2012, and FrameNet.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Survey of Pretraining on graphs: Taxonomy, methods, and Applications

arXiv

引用

arXiv 2022年

作者： Xia, Jun Zhu, Yanqiao Du, Yuanqi Li, Stan Z. School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study China Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Computer Science George Mason University United States

Pre-trained language Models (PLMs) such as BERT have revolutionized the landscape of natural language processing (NLP). Inspired by their proliferation, tremendous efforts have been devoted to pre-trained graph models (PGMs) recently. Owing to its huge model parameters, PGMs can capture abundant knowledge from massive labeled and unlabeled graph data. The knowledge implicitly encoded in model parameters can benefit various downstream tasks and help to alleviate several fundamental issues of learning on graphs. In this paper, we provide a comprehensive survey for PGMs. We first briefly present the limitations of graph representation learning and thus introduce the motivation for graph pre-training. Next, we systematically categorize existing PGMs based on a taxonomy from five different perspectives including the history, model architectures, pre-training strategies, tunning strategies and applications. Finally, we outline several promising research directions that can serve as a guideline for future studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

R-VGAE: Relational-variational graph Autoencoder for Unsupervised Prerequisite Chain Learning 28

R-VGAE: Relational-variational Graph Autoencoder for Unsuper...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Li, Irene Fabbri, Alexander Hingmire, Swapnil Radev, Dragomir Yale University United States India

ISBN: (纸本)9781952148279

The task of concept prerequisite chain learning is to automatically determine the existence of prerequisite relationships among concept pairs. In this paper, we frame learning prerequisite relationships among concepts as an unsupervised task with no access to labeled concept pairs during training. We propose a model called the Relational-variational graph AutoEncoder (R-VGAE) to predict concept relations within a graph consisting of concept and resource nodes. Results show that our unsupervised approach outperforms graph-based semi-supervised methods and other baseline methods by up to 9.77% and 10.47% in terms of prerequisite relation prediction accuracy and F1 score. Our method is notably the first graph-based model that attempts to make use of deep learning representations for the task of unsupervised prerequisite learning. We also expand an existing corpus which totals 1, 717 English natural language processing (NLP)-related lecture slide files and manual concept pair annotations over 322 topics. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, proceedings of the Conference. All rights reserved.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

How to Represent Paintings: A Painting Classification Using Artistic Comments

引用

SENSORS 2021年第6期21卷 1940-1940页

作者： Zhao, Wentao Zhou, Dalin Qiu, Xinguo Jiang, Wei Zhejiang Univ Technol Coll Mech Engn Hangzhou 310023 Peoples R China Zhejiang Inst Mech & Elect Engn Sch Intelligent Transportat Hangzhou 310053 Peoples R China Univ Portsmouth Sch Comp Portsmouth PO1 3HE Hants England

The goal of large-scale automatic paintings analysis is to classify and retrieve images using machine learning techniques. The traditional methods use computer vision techniques on paintings to enable computers to represent the art content. In this work, we propose using a graph convolutional network and artistic comments rather than the painting color to classify type, school, timeframe and author of the paintings by implementing natural language processing (NLP) techniques. first, we build a single artistic comment graph based on co-occurrence relations and document word relations and then train an art graph convolutional network (ArtGCN) on the entire corpus. The nodes, which include the words and documents in the topological graph are initialized using a one-hot representation;then, the embeddings are learned jointly for both words and documents, supervised by the known-class training labels of the paintings. Through extensive experiments on different classification tasks using different input sources, we demonstrate that the proposed methods achieve state-of-art performance. In addition, ArtGCN can learn word and painting embeddings, and we find that they have a major role in describing the labels and retrieval paintings, respectively.

关键词： graph convolutional networks art classification machine learning natural language processing

来源：评论

学校读者我要写书评

暂无评论

GRADE Automatic graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems

GRADE Automatic Graph-Enhanced Coherence Metric for Evaluati...

引用

Conference on Empirical methods in natural language processing (EMNLP)

作者： Huang, Lishan Ye, Zheng Qin, Jinghui Lin, Liang Liang, Xiaodan Sun Yat Sen Univ Guangzhou Peoples R China Dark Matter AI Inc Guangzhou Peoples R China

ISBN: (纸本)9781952148606

Automatically evaluating dialogue coherence is a challenging but high-demand ability for developing high-quality open-domain dialogue systems. However, current evaluation metrics consider only surface features or utterance-level semantics, without explicitly considering the fine-grained topic transition dynamics of dialogue flows. Here, we first consider that the graph structure constituted with topics in a dialogue can accurately depict the underlying communication logic, which is a more natural way to produce persuasive metrics. Capitalized on the topic-level dialogue graph, we propose a new evaluation metric GRADE, which stands for graph-enhanced Representations for Automatic Dialogue Evaluation. Specifically, GRADE incorporates both coarse-grained utterance-level contextualized representations and fine-grained topic-level graph representations to evaluate dialogue coherence. The graph representations are obtained by reasoning over topic-level dialogue graphs enhanced with the evidence from a commonsense graph, including k-hop neighboring representations and hop-attention weights. Experimental results show that our GRADE significantly outperforms other state-of-the-art metrics on measuring diverse dialogue models in terms of the Pearson and Spearman correlations with human judgements. Besides, we release a new large-scale human evaluation benchmark to facilitate future research on automatic metrics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

结构信息增强的文献分类方法研究

引用

农业图书情报学报 2023年第3期35卷 15-24页

作者：安波中国社会科学院民族学与人类学研究所北京100081 中国科学院软件研究所北京100190

[目的/意义]针对传统文献分类方法未能充分利用文献结构信息的问题,本文提出使用关键词-文献图网络构建文献之间的结构信息,并用于增强传统基于文献内容的分类方法。[方法/过程]本文借助图卷积神经网络建模关键词-文献图数据,学习文献... 详细信息

[目的/意义]针对传统文献分类方法未能充分利用文献结构信息的问题,本文提出使用关键词-文献图网络构建文献之间的结构信息,并用于增强传统基于文献内容的分类方法。[方法/过程]本文借助图卷积神经网络建模关键词-文献图数据,学习文献在图网络中的节点表示。同时使用Bert+BiLSTM学习文献的内容表示。然后,我们将文献的节点表示与内容表示进行拼接,得到融合文献结构信息和文本语义信息的表示,并基于该表示开展文献分类。[结果/结论]实验结果表明,文献的结构信息能够提升文献分类的性能,但单一的结构信息并不能很好地实现文献分类。通过错误分析,我们发现模型在处理包含新兴交叉科学和新概念的文献时容易出现分类错误,表明模型在处理这类数据时还有一定的局限性,是未来需要继续优化的方向。

关键词：文献分类图卷积神经网络关键词-文献图语义关联知识组织自然语言处理

来源：评论

学校读者我要写书评

暂无评论

CoDEx: A Comprehensive Knowledge graph Completion Benchmark

CoDEx: A Comprehensive Knowledge Graph Completion Benchmark

引用

Conference on Empirical methods in natural language processing (EMNLP)

作者： Safavi, Tara Koutra, Danai Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9781952148606

We present CoDEx, a set of knowledge graph Completion Datasets Extracted from Wiki-data and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. In terms of scope, CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible but verified to be false. To characterize CoDEx, we contribute thorough empirical analyses and benchmarking experiments. first, we analyze each CoDEx dataset in terms of logical relation patterns. Next, we report baseline link prediction and triple classification results on CoDEx for five extensively tuned embedding models. Finally, we differentiate CoDEx from the popular FB15K-237 knowledge graph completion dataset by showing that CoDEx covers more diverse and interpretable content, and is a more difficult link prediction benchmark. Data, code, and pretrained models are available at https://***/2EPbrJs.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Advancing Surgical VQA with Scene graph Knowledge

arXiv

引用

arXiv 2023年

作者： Yuan, Kun Kattel, Manasi Lavanchy, Joël L. Navab, Nassir Srivastav, Vinkle Padoy, Nicolas ICube University of Strasbourg CNRS Strasbourg France IHU Strasbourg Strasbourg France CAMP Technische Universität München Munich Germany

Purpose: The modern operating room is becoming increasingly complex, requiring innovative intra-operative support systems. While the focus of surgical data science has largely been on video analysis, integrating surgical computer vision with natural language capabilities is emerging as a necessity. Our work aims to advance Visual Question Answering (VQA) in the surgical context with scene graph knowledge, addressing two main challenges in the current surgical VQA systems: removing question-condition bias in the surgical VQA dataset and incorporating scene-aware reasoning in the surgical VQA model design. methods: first, we propose a Surgical Scene graph-based dataset, SSG-VQA, generated by employing segmentation and detection models on publicly available datasets. We build surgical scene graphs using spatial and action information of instruments and anatomies. These graphs are fed into a question engine, generating diverse QA pairs. Our SSG-VQA dataset provides a more complex, diverse, geometrically grounded, unbiased, and surgical action-oriented dataset compared to existing surgical VQA datasets. We then propose SSG-VQA-Net, a novel surgical VQA model incorporating a lightweight Scene-embedded Interaction Module (SIM), which integrates geometric scene knowledge in the VQA model design by employing cross-attention between the textual and the scene features. Results: Our comprehensive analysis of the SSG-VQA dataset shows that SSG-VQA-Net outperforms existing methods across different question types and complexities. We highlight that the primary limitation in the current surgical VQA systems is the lack of scene knowledge to answer complex queries. Conclusion: We present a novel surgical VQA dataset and model and show that results can be significantly improved by incorporating geometric scene features in the VQA model design. The source code and the dataset will be made publicly available at: https://***/CAMMA-public/SSG-VQA © 2023, CC BY.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

PathQG: Neural Question Generation from Facts

PathQG: Neural Question Generation from Facts

引用

Conference on Empirical methods in natural language processing (EMNLP)

作者： Wang, Siyuan Wei, Zhongyu Fan, Zhihao Huang, Zengfeng Sun, Weijian Zhang, Qi Huang, Xuanjing Fudan Univ Sch Data Sci Shanghai Peoples R China Fudan Univ Res Inst Intelligent & Complex Syst Shanghai Peoples R China Huawei Technol Co Ltd Beijing Peoples R China Fudan Univ Sch Comp Sci Shanghai Peoples R China

ISBN: (纸本)9781952148606

Existing research for question generation encodes the input text as a sequence of tokens without explicitly modeling fact information. These models tend to generate irrelevant and uninformative questions. In this paper, we explore to incorporate facts in the text for question generation in a comprehensive way. We present a novel task of question generation given a query path in the knowledge graph constructed from the input text. We divide the task into two steps, namely, query representation learning and query-based question generation. We formulate query representation learning as a sequence labeling problem for identifying the involved facts to form a query and employ an RNN-based generator for question generation. We first train the two modules jointly in an end-to-end fashion, and further enforce the interaction between these two modules in a variational framework. We construct the experimental datasets on top of SQuAD and results show that our model outperforms other state-of-the-art approaches, and the performance margin is larger when target questions are complex. Human evaluation also proves that our model is able to generate relevant and informative questions.(1)

关键词： Knowledge graph

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：