自然语言领域中图神经网络模型（GNN）应用现状（论文）

点击上方，选择星标或置顶，每天给你送干货！

阅读大概需要21分钟

跟随小博主，每天进步一丢丢

整理： 深度学习与NLP

    本文整理了图神经网络模型（Graph Neural Network，GNN）在自然语言处理领域的各个任务中使用的一些论文。涉及GNN在文本分类、信息抽取、问答、可视化问答、文本生成、知识图谱和文本错误检测相关的应用；还整理了自然语言各个顶会ACL、EMNLP、KDD、NAACL中GNN应用于NLP的一些论文。

    本资源整理自网络，源地址：https://github.com/IndexFziQ/GNN4NLP-Papers

NLP各类任务

    基础的NLP任务

    1.Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks. Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya and Partha Talukdar. ACL 2019

    2.A Lexicon-Based Graph Neural Network for Chinese NER. Tao Gui, Yicheng Zou and Qi Zhang. EMNLP 2019

    文本分类

    1.Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks. Chen Zhang, Qiuchi Li and Dawei Song. EMNLP 2019

    2.Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification. Linmei Hu, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li. EMNLP 2019

    3.Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks. Binxuan Huang and Kathleen M. Carley. EMNLP 2019

    问答系统

    1.BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering. Yu Cao, Meng Fang and Dacheng Tao. NAACL-HLT 2019. 

    2.Question Answering by Reasoning Across Documents with Graph Convolutional Networks. Nicola De Cao, Wilker Aziz and Ivan Titov. NAACL-HLT 2019.

    3.Cognitive Graph for Multi-Hop Reading Comprehension at Scale. Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang and Jie Tang. ACL 2019 

    4.Dynamically Fused Graph Network for Multi-hop Reasoning. Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang and Yong Yu. ACL 2019 

    5.Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs. Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He and Bowen Zhou. ACL 2019

    6.DialogueGCN A Graph Convolutional Neural Network for Emotion Recognition in Conversation. Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya and Alexander Gelbukh. EMNLP 2019

    7.GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification. Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li and Maosong Sun. ACL 2019

    8.Kernel Graph Attention Network for Fact Verification. Zhenghao Liu, Chenyan Xiong and Maosong Sun. Arxiv 2019 

    9.Reasoning Over Semantic-Level Graph for Fact Checking. Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang and Jian Yin. Arxiv 2019

    信息抽取

    1.Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks. Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang and Huajun Chen. NAACL-HLT 2019.

  2.Attention Guided Graph Convolutional Networks for Relation Extraction. Zhijiang Guo, Yan Zhang and Wei Lu. ACL 2019  

    3.Graph Neural Networks with Generated Parameters for Relation Extraction. Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-seng Chua and Maosong Sun. ACL 2019 

    4.GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction. Tsu-Jui Fu, Peng-Hsuan Li and Wei-Yun Ma. ACL 2019  

    文本生成

    1.Text Generation from Knowledge Graphs with Graph Transformers. Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata and Hannaneh Hajishirzi. NAACL-HLT 2019.  

    2.Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model. Wei Li, Jingjing Xu, Yancheng He, Shengli Yan, Yunfang Wu and Xu Sun. ACL 2019  

    3.Enhancing AMR-to-Text Generation with Dual Graph Representations. Leonardo F. R. Ribeiro, Claire Gardent and Iryna Gurevych. EMNLP 2019 

    知识图谱

    1.Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks. Namyong Park, Andrey Kan, Xin Luna Dong, Tong Zhao and Christos Faloutsos. KDD 2019 

    文本错误检测

    1.Abusive Language Detection with Graph Convolutional Networks. Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis and Ekaterina Shutova. NAACL-HLT 2019. 

    2.Encoding Social Information with Graph Convolutional Networks for Political Perspective Detection in News Media. Chang Li and Dan Goldwasser. ACL 2019 

    可视化问答

    1.Relation-Aware Graph Attention Network for Visual Question Answering. Linjie Li, Zhe Gan, Yu Cheng and Jingjing Liu.ICCV 2019 

    2.Language-Conditioned Graph Networks for Relational Reasoning. Ronghang Hu, Anna Rohrbach, Trevor Darrell and Kate Saenko. ICCV 2019  

    3.Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension. Daesik Kim, Seonhoon Kim and Nojun Kwak. ACL 2019 

    基础理论

    1.HetGNN: Heterogeneous Graph Neural Network. Chuxu Zhang, Dongjin Song, Chao Huang, Ananthram Swami and Nitesh V. Chawla. KDD 2019 

    2.GMNN: Graph Markov Neural Networks. Meng Qu, Yoshua Bengio and Jian Tang. ICML 2019  

最新顶会论文

    NAACL-HLT 2019

    1.BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering. Yu Cao, Meng Fang and Dacheng Tao. NAACL-HLT 2019.  

    2.Abusive Language Detection with Graph Convolutional Networks. Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis and Ekaterina Shutova. NAACL-HLT 2019. 

    3.Text Generation from Knowledge Graphs with Graph Transformers. Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata and Hannaneh Hajishirzi. NAACL-HLT 2019.  

    4.Question Answering by Reasoning Across Documents with Graph Convolutional Networks. Nicola De Cao, Wilker Aziz and Ivan Titov. NAACL-HLT 2019. 

    5.Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks. Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang and Huajun Chen. NAACL-HLT 2019. 

    KDD 2019

    1.Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks. Namyong Park, Andrey Kan, Xin Luna Dong, Tong Zhao and Christos Faloutsos. KDD 2019 

    2.HetGNN: Heterogeneous Graph Neural Network. Chuxu Zhang, Dongjin Song, Chao Huang, Ananthram Swami and Nitesh V. Chawla. KDD 2019 

    ICML 2019

    1.GMNN: Graph Markov Neural Networks. Meng Qu, Yoshua Bengio and Jian Tang. ICML 2019  

    ICCV 2019

    1.Relation-Aware Graph Attention Network for Visual Question Answering. Linjie Li, Zhe Gan, Yu Cheng and Jingjing Liu.ICCV 2019 

    2.Language-Conditioned Graph Networks for Relational Reasoning. Ronghang Hu, Anna Rohrbach, Trevor Darrell and Kate Saenko. ICCV 2019  

    ACL 2019

    1.Attention Guided Graph Convolutional Networks for Relation Extraction. Zhijiang Guo, Yan Zhang and Wei Lu. ACL 2019  

    2.GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification. Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li and Maosong Sun. ACL 2019  

    3.Cognitive Graph for Multi-Hop Reading Comprehension at Scale. Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang and Jie Tang. ACL 2019  

    4.Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model. Wei Li, Jingjing Xu, Yancheng He, Shengli Yan, Yunfang Wu and Xu Sun. ACL 2019  

    5.Dynamically Fused Graph Network for Multi-hop Reasoning. Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang and Yong Yu. ACL 2019 

    6.Encoding Social Information with Graph Convolutional Networks for Political Perspective Detection in News Media. Chang Li and Dan Goldwasser. ACL 2019 

    7.Graph Neural Networks with Generated Parameters for Relation Extraction. Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-seng Chua and Maosong Sun. ACL 2019 

    8.Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks. Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya and Partha Talukdar. ACL 2019 

    9.GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction. Tsu-Jui Fu, Peng-Hsuan Li and Wei-Yun Ma. ACL 2019  

    10.Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs. Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He and Bowen Zhou. ACL 2019 

    11.Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension. Daesik Kim, Seonhoon Kim and Nojun Kwak. ACL 2019 

    EMNLP 2019

    1.A Lexicon-Based Graph Neural Network for Chinese NER. Tao Gui, Yicheng Zou and Qi Zhang. EMNLP 2019 

    2.Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks. Chen Zhang, Qiuchi Li and Dawei Song. EMNLP 2019 

    3.DialogueGCN A Graph Convolutional Neural Network for Emotion Recognition in Conversation. Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya and Alexander Gelbukh. EMNLP 2019 

    4.Enhancing AMR-to-Text Generation with Dual Graph Representations. Leonardo F. R. Ribeiro, Claire Gardent and Iryna Gurevych. EMNLP 2019 

    5.Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification. Linmei Hu, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li. EMNLP 2019 

    6.Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks. Binxuan Huang and Kathleen M. Carley. EMNLP 2019 

    ICLR 2020 under review

    1.Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph Reasoning. 

    2.Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation. 

    3.Reasoning-Aware Graph Convolutional Network for Visual Question Answering. 

    4.GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension. 

    5.MEMORY-BASED GRAPH NETWORKS. 

 GNN相关的综述文章

    thunlp/GNNPapers

    nnzhan/Awesome-Graph-Neural-Networks

---

方便交流学习，备注： 昵称-学校（公司）-方向，进入DL&NLP交流群。

方向有很多： 机器学习、深度学习，python，情感分析、意见挖掘、句法分析、机器翻译、人机对话、知识图谱、语音识别等。

记得备注呦

推荐阅读：

【ACL 2019】腾讯AI Lab解读三大前沿方向及20篇入选论文

【一分钟论文】IJCAI2019 | Self-attentive Biaffine Dependency  Parsing

【一分钟论文】 NAACL2019-使用感知句法词表示的句法增强神经机器翻译

【一分钟论文】Semi-supervised Sequence Learning半监督序列学习

【一分钟论文】Deep Biaffine Attention for Neural Dependency Parsing

详解Transition-based Dependency parser基于转移的依存句法解析器

经验 | 初入NLP领域的一些小建议

学术 | 如何写一篇合格的NLP论文

干货 | 那些高产的学者都是怎样工作的？

一个简单有效的联合模型

近年来NLP在法律领域的相关研究工作

---

让更多的人知道你“在看”