Filters








2,114 Hits in 6.1 sec

Incorporating Commonsense Knowledge into Story Ending Generation via Heterogeneous Graph Networks [article]

Jiaan Wang, Beiqi Zou, Zhixu Li, Jianfeng Qu, Pengpeng Zhao, An Liu, Lei Zhao
2022 arXiv   pre-print
The auxiliary tasks are jointly optimized with the primary story ending generation task in a multi-task learning strategy.  ...  In this paper, we propose a Story Heterogeneous Graph Network (SHGN) to explicitly model both the information of story context at different granularity levels and the multi-grained interactive relations  ...  [10] propose a multi-level graph convolutional network to capture the dependency relations of input sentences.  ... 
arXiv:2201.12538v1 fatcat:4xk3j4s6lve6pkh4cg3tasnd2u

Graph Convolutional Encoders for Syntax-aware Neural Machine Translation [article]

Jasmijn Bastings, Ivan Titov, Wilker Aziz, Diego Marcheggiani, Khalil Sima'an
2020 arXiv   pre-print
We rely on graph-convolutional networks (GCNs), a recent class of neural networks developed for modeling graph-structured data.  ...  ., on top of bidirectional RNNs or convolutional neural networks).  ...  Graph Convolutional Networks We will now describe the Graph Convolutional Networks (GCNs) of Kipf and Welling (2016) .  ... 
arXiv:1704.04675v4 fatcat:nlygyogo4fcfpbiaixf5yornre

Graph Convolutional Encoders for Syntax-aware Neural Machine Translation

Joost Bastings, Ivan Titov, Wilker Aziz, Diego Marcheggiani, Khalil Simaan
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
We rely on graph-convolutional networks (GCNs), a recent class of neural networks developed for modeling graph-structured data.  ...  ., on top of bidirectional RNNs or convolutional neural networks).  ...  Graph Convolutional Networks We will now describe the Graph Convolutional Networks (GCNs) of Kipf and Welling (2016) .  ... 
doi:10.18653/v1/d17-1209 dblp:conf/emnlp/BastingsTAMS17 fatcat:uzpnh3uw5ngbnjtaxflt7ioihm

Matching Article Pairs with Graphical Decomposition and Convolutions [article]

Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu
2019 arXiv   pre-print
network.  ...  We then match a pair of articles by comparing the sentences that enclose the same concept vertex through a series of encoding techniques, and aggregate the matching signals through a graph convolutional  ...  Graph Convolution Network for semantic matching.  ... 
arXiv:1802.07459v2 fatcat:x436jyfbxjeb7euf5fmbp5nxsa

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
Ouyang, Learning Localized Representations of Point Clouds With Graph-Convolutional Generative Adversarial Networks.  ...  Su, H., +, TMM 2021 tional Generative Adversarial Networks. Valsesia, D., +, TMM 2021 402-Convolutional neural networks Enabling Artistic Control Over Pattern Density and Stroke Strength.  ...  ., Low-Rank Pairwise Align- ment Bilinear Network For Few-Shot Fine-Grained Image Classification; TMM 2021 1666-1680 Huang, H., see 1855 -1867 Huang, H., see Jiang, X., TMM 2021 2602-2613 Huang, J.,  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

A Survey on the Use of Graph Convolutional Networks for Combating Fake News

Iraklis Varlamis, Dimitrios Michail, Foteini Glykou, Panagiotis Tsantilas
2022 Future Internet  
The current work focuses on the popular and promising graph representation techniques and performs a survey of the works that employ Graph Convolutional Networks (GCNs) to the task of detecting fake news  ...  The combat against fake news and disinformation is an ongoing, multi-faceted task for researchers in social media and social networks domains, which comprises not only the detection of false facts in published  ...  A similar neural network structure, with Convolutional Neural Network units (CNNs) instead of GRUs, generates a second representation of the news' spreading path.  ... 
doi:10.3390/fi14030070 fatcat:aha4yr6rsjcefhc3cporwtjg7e

Learning and Interpreting Multi-Multi-Instance Learning Networks [article]

Alessandro Tibo, Manfred Jaeger, Paolo Frasconi
2020 arXiv   pre-print
such as convolutional networks on graphs, while at the same time it supports a general approach to interpret the learnt model, as well as explain individual predictions.  ...  We finally present experiments on text classification, on citation graphs, and social graph data, which show that our model obtains competitive results with respect to accuracy when compared to other approaches  ...  AT was with DINFO, Università di Firenze, when this work was initially submitted.  ... 
arXiv:1810.11514v4 fatcat:2tiy27ez6jbg7daee5x6jjnxmu

Urban Land Cover Classification of High-Resolution Aerial Imagery Using a Relation-Enhanced Multiscale Convolutional Network

Chun Liu, Doudou Zeng, Hangbin Wu, Yin Wang, Shoujun Jia, Liang Xin
2020 Remote Sensing  
However, the traditional CNNs using convolution operations with local receptive fields are not sufficient to model global contextual relations between objects.  ...  A dense connectivity pattern and parallel multi-kernel convolution are combined to build a lightweight and varied receptive field sizes model.  ...  It is a relatively small town with many detached buildings and small multi-story buildings [53].  ... 
doi:10.3390/rs12020311 fatcat:pa4645kxzzdjzhizzynfsbjwhe

A Survey of the Usages of Deep Learning in Natural Language Processing [article]

Daniel W. Otter, Julian R. Medina, Jugal K. Kalita
2019 arXiv   pre-print
A discussion of the current state of the art is then provided along with recommendations for future research in the field.  ...  Over the last several years, the field of natural language processing has been propelled forward by an explosion in the use of deep learning models.  ...  [208] , who used LSTMs to generate stories, providing an input to specify whether the story should have a happy or sad ending.  ... 
arXiv:1807.10854v3 fatcat:ajyv5o743naixeo5c5y6p6tg3e

Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification

Hao Peng, Jianxin Li, Senzhang Wang, Lihong Wang, Qiran Gong, Renyu Yang, Bo Li, Philip Yu, Lifang He
2019 IEEE Transactions on Knowledge and Data Engineering  
Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches.  ...  In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification.  ...  Directory code classes are organized in a hierarchy of 4 levels with a typical tree structure.  ... 
doi:10.1109/tkde.2019.2959991 fatcat:wi5guiyng5bqxeuwggro6ysgue

Pruned Graph Neural Network for Short Story Ordering [article]

Melika Golestani, Zeinab Borhanifard, Farnaz Tahmasebian, Heshaam Faili
2022 arXiv   pre-print
This paper is proposing a new approach based on the graph neural network approach to encode a set of sentences and learn orderings of short stories.  ...  We propose a new method for constructing sentence-entity graphs of short stories to create the edges between sentences and reduce noise in our graph by replacing the pronouns with their referring entities  ...  Encoding sentences with graph convolutional networks for semantic role labeling.  ... 
arXiv:2203.06778v1 fatcat:kauj2v2fazeilesgoc3jmea6ju

A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data

Adam Trischler, Zheng Ye, Xingdi Yuan, Jing He, Philip Bachman
2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Perspectives range from the word level to sentence fragments to sequences of sentences; the networks operate only on word-embedding representations of text.  ...  We tackle the dataset with a neural approach, harnessing simple neural networks arranged in a parallel hierarchy.  ...  ., 2015) , both deep, end-to-end recurrent models with attention mechanisms, and also developed an attention-based convolutional network, the HABCNN.  ... 
doi:10.18653/v1/p16-1041 dblp:conf/acl/TrischlerYYHB16 fatcat:leb4wjde3zeuvdfneyd6rc24hy

Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph

Zunwang Ke, Zhe Li, Chenzhi Zhou, Jiabao Sheng, Wushour Silamu, Qinglang Guo
2020 Symmetry  
To this end, we propose KZWANG, a framework for rumor detection that provides sufficient domain knowledge to classify rumors accurately, and semantic information and a propagation heterogeneous graph are  ...  Existing rumor detection methods have relied on finding cues from only user-generated content, user profiles, or the structures of wide propagation.  ...  In fact, a CNN is not designed to study representations of high-level from structured data, but the graph convolutional network (GCN) can do [14] .  ... 
doi:10.3390/sym12111806 fatcat:ahelbdk7qrel5e54ifokqkrpma

Understanding in Artificial Intelligence [article]

Stefan Maetschke and David Martinez Iraola and Pieter Barnard and Elaheh ShafieiBavani and Peter Zhong and Ying Xu and Antonio Jimeno Yepes
2021 arXiv   pre-print
Convolutional neural networks [150, 151] , fully-convolutional neural networks [152, 153] , region-based convolutional neural networks [154, 155, 156, 157] , and graph neural networks [158, 159] have  ...  To this end, a general end-to-end graph-to-sequence neural encoder-decoder model is proposed for mapping an input graph to a sequence of vectors using an attention-based LSTM method to decode the target  ... 
arXiv:2101.06573v1 fatcat:nlp6h5toh5f6lpwjsafn6gulbq

Functional Annotation of Human Cognitive States using Deep Graph Convolution [article]

Yu Zhang, Lo&iumlc Tetrel, Bertrand Thirion, Pierre Bellec
2020 bioRxiv   pre-print
By leveraging our prior knowledge on network organization of human brain cognition, we constructed deep graph convolutional neural networks to annotate cognitive states by first mapping the task-evoked  ...  fMRI response onto a brain graph, propagating brain dynamics among interconnected brain regions and functional networks, and generating state-specific representations of recorded brain activity.  ...  First, the network is enriched with more low-level graph filters, which provides more diverse features for the high-level graph convolutions.  ... 
doi:10.1101/2020.04.24.060657 fatcat:k4awdrkazzcqdla3a37ehxczk4
« Previous Showing results 1 — 15 out of 2,114 results