777 Hits in 4.3 sec

Semantic Graph Convolutional Network for Implicit Discourse Relation Classification [article]

Yingxue Zhang, Ping Jian, Fandong Meng, Ruiying Geng, Wei Cheng, Jie Zhou
2019 arXiv   pre-print
In this paper, we propose a novel and effective Semantic Graph Convolutional Network (SGCN) to enhance the modeling of inter-argument semantics on a deeper interaction level for implicit discourse relation  ...  Implicit discourse relation classification is of great importance for discourse parsing, but remains a challenging problem due to the absence of explicit discourse connectives communicating these relations  ...  Conclusion We propose a novel and effective Semantic Graph Convolutional Network (SGCN) for implicit discourse relation classification, which can model the inter-arguments semantics structurally and capture  ... 
arXiv:1910.09183v1 fatcat:lqnyuwfcovaqrpysmd4gieelvm

Self-organizing incremental and graph convolution neural network for English implicit discourse relation recognition

Yubo Geng
2021 EAI Endorsed Transactions on Scalable Information Systems  
A classification model based on self-organizing incremental and graph convolutional neural network is constructed to obtain the argument representation which is helpful for English implicit discourse relation  ...  To solve this problem, this paper proposes a self-organizing incremental and graph convolution neural network for English implicit discourse relation recognition.  ...  Conclusions In this paper, a graph convolutional neural network model based on self-organizing increment and interactive attention mechanism is proposed to recognize implicit discourse relations.  ... 
doi:10.4108/eai.22-11-2021.172215 fatcat:dx4swsvbtnbw3bww3cxz6ohs7q

A Survey of Implicit Discourse Relation Recognition [article]

Wei Xiang, Bang Wang
2022 arXiv   pre-print
The task of implicit discourse relation recognition (IDRR) is to detect implicit relation and classify its sense between two text segments without a connective.  ...  Finally, we discuss future research directions for discourse relation analysis.  ...  A graph convolutional network is used to extract interactive features from the semantic interaction graph.  ... 
arXiv:2203.02982v1 fatcat:ubublxw2fnfdpexgw4jslj76tm

Context-specific Heterogeneous Graph Convolutional Network for Implicit Sentiment Analysis

Enguang Zuo, Hui Zhao, Bo Chen, Qiuchang Chen
2020 IEEE Access  
INDEX TERMS Implicit sentiment, sentiment analysis, heterogeneous graph, graph convolutional network (GCN). VOLUME 8, 2020 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  Graph convolutional network (GCN) techniques have been widely applied for sentiment analysis since they are capable of learning from complex structures and preserving global information.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their valuable remarks and comments.  ... 
doi:10.1109/access.2020.2975244 fatcat:eztswbwtvbaatajonbmcfajppy

Towards Causal Explanation Detection with Pyramid Salient-Aware Network [article]

Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao
2020 arXiv   pre-print
PSAN can assist in causal explanation detection via capturing the salient semantics of discourses contained in their keywords with a bottom graph-based word-level salient network.  ...  Furthermore, PSAN can modify the dominance of discourses via a top attention-based discourse-level salient network to enhance explanatory semantics of messages.  ...  The graph convolutional network (GCN) (Kipf and Welling, 2016) is a generalization of convolutional neural network (LeCun et al., 1998) for encoding graphs.  ... 
arXiv:2009.10288v2 fatcat:haerjf5ksff67m4b3o3bb3yaw4

Measuring Semantic Coherence of a Conversation [article]

Svitlana Vakulenko, Maarten de Rijke, Michael Cochez, Vadim Savenkov, Axel Polleres
2018 arXiv   pre-print
We propose and evaluate graph-based and machine learning-based approaches for measuring semantic coherence using knowledge graphs, their vector space embeddings and word embedding models, as sources of  ...  We introduce the task of measuring semantic (in)coherence in a conversation with respect to background knowledge, which relies on the identification of semantic relations between concepts introduced during  ...  Convolutional neural network.  ... 
arXiv:1806.06411v1 fatcat:5htffhqbtndvxgpwq7jdx6bzu4

Classifying Diagrams and Their Parts using Graph Neural Networks: A Comparison of Crowd-Sourced and Expert Annotations [article]

Tuomo Hiippala
2019 arXiv   pre-print
graph neural networks.  ...  This article reports on two experiments that evaluate how effectively crowd-sourced and expert-annotated graphs can represent the multimodal structure of diagrams for representation learning using various  ...  Graph Neural Networks I evaluated the following graph neural network architectures for both graph and node classification tasks: • Graph Convolutional Network (GCN) (Kipf and Welling, 2017) • Simplifying  ... 
arXiv:1912.02866v1 fatcat:u4snprup2jhkvazmoew5rhibf4

Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains

Wei Shi, Vera Demberg
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Implicit discourse relation classification is one of the most difficult tasks in discourse parsing.  ...  Current discourse relation classifiers fall short in this respect.  ...  We'd like to thank all the reviewers for their insightful and valuable comments.  ... 
doi:10.18653/v1/d19-1586 dblp:conf/emnlp/ShiD19 fatcat:rvqmcvdijfdfxondi2ctst5yhq

Variational Neural Discourse Relation Recognizer [article]

Biao Zhang, Deyi Xiong, Jinsong Su, Qun Liu, Rongrong Ji, Hong Duan, Min Zhang
2016 arXiv   pre-print
Implicit discourse relation recognition is a crucial component for automatic discourselevel analysis and nature language understanding.  ...  VarNDRR establishes a directed probabilistic model with a latent continuous variable that generates both a discourse and the relation between the two arguments of the discourse.  ...  We also thank the anonymous reviewers for their insightful comments.  ... 
arXiv:1603.03876v2 fatcat:klpb4xt37rfhdpxugqihixe444

Variational Neural Discourse Relation Recognizer

Biao Zhang, Deyi Xiong, jinsong su, Qun Liu, Rongrong Ji, Hong Duan, Min Zhang
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
Generally, discourse relations can be divided into two categories: explicit and implicit, which can be illustrated in the following example: The company was disappointed by the ruling. because The obligation  ...  We also thank the anonymous reviewers for their insightful comments.  ...  . • SCNN: a shallow convolutional neural network proposed by Zhang et al. (2015) .  ... 
doi:10.18653/v1/d16-1037 dblp:conf/emnlp/ZhangXSLJDZ16 fatcat:rdm6xgbl6zg5zbpg4wapyrx57i

Learning Procedures from Text

Hogun Park, Hamid Reza Motahari Nezhad
2018 Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18  
Recently, extracting semantic relations from the procedural text has been actively explored.  ...  To identify the relationships, we propose an end-to-end neural network architecture, which can selectively learn important procedure-specific relationships.  ...  The task of implicit discourse relationship classification is to recognize how two adjacent sentences are associated without explicit discourse markers (e.g. "because").  ... 
doi:10.1145/3184558.3186347 dblp:conf/www/ParkM18 fatcat:eq4s4pb4lvanho6hq57axwy4ye

Causality Mining in Natural Languages Using Machine and Deep Learning Techniques: A Survey

Wajid Ali, Wanli Zuo, Rahman Ali, Xianglin Zuo, Gohar Rahman
2021 Applied Sciences  
Causality (cause-effect relations) serves as an essential category of relationships, which plays a significant role in question answering, future events predication, discourse comprehension, decision making  ...  While, decades of development techniques for CM are still prone to performance enhancement, especially for ambiguous and implicitly expressed causalities.  ...  SemEvel2007 Benchmark dataset to 7. [49] task-4 is applied for finding 7 frequently occurring semantic Events pair patterns of 7 relation types. let the evaluation of diverse semantic relation classification  ... 
doi:10.3390/app112110064 fatcat:btv66da5x5a73auogv5d3lp2bi

Dialogue Graph Modeling for Conversational Machine Reading [article]

Siru Ouyang, Zhuosheng Zhang, Hai Zhao
2021 arXiv   pre-print
Specifically, Discourse Graph is designed to learn explicitly and extract the discourse relation among rule texts as well as the extra knowledge of scenario; Decoupling Graph is used for understanding  ...  And finally a global graph for fusing the information together and reply to the user with our final decision being either "Yes/No/Irrelevant" or to ask a follow-up question to clarify.  ...  Acknowledgments We would like to thank all the anonymous reviewers for their helpful comments and suggestions. Also thanks to Max Bartolo for evaluating our submitted models on the hidden test set.  ... 
arXiv:2012.14827v3 fatcat:55x2wnxkjvhnpa47czlqxcbx24

Genetic Optimization in Hybrid Level Sentiment Analysis for Opinion Classification

Gatta Sravya
2020 International Journal of Advanced Trends in Computer Science and Engineering  
To overcome this problem and to train the machine to perfection, we introduced a feature optimization algorithm with CNN (Convolutional Neural Network) as a classification algorithm.  ...  Yet many approaches and models were developed for this problem, classification problem still remained.  ...  has convolutional and recurrent neural networks.  ... 
doi:10.30534/ijatcse/2020/81922020 fatcat:nchkxhj7znannj62nnhpxu22x4

Table of Contents

2021 IEEE/ACM Transactions on Audio Speech and Language Processing  
Zhu Learning Context-Aware Convolutional Filters for Implicit Discourse Relation Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Guanason Detection and Classification of Acoustic Scenes and Events Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks . . . . . . .  ... 
doi:10.1109/taslp.2021.3137066 fatcat:ocit27xwlbagtjdyc652yws4xa
« Previous Showing results 1 — 15 out of 777 results