本周论文推荐 -- 对抗生成网络、知识图谱补全、对话系统、文本生成

导读

下面论文列表为本小组同学推荐和整理，关于论文细节请联系论文作者。内容 涵盖以下研究方向： 对抗生成网络、知识图谱补全、对话系统、文本生成。

来自：RUC AI Box 公众号

本周论文推荐

 1  

 对抗生成网络 

• Adversarial Training and Provable Defenses: Bridging the Gap. Mislav Balunovic, Martin Vechev. ICLR 2020

• Implicit Bias of Gradient Descent based Adversarial Training on Separable Data. Yan Li, Ethan X.Fang, Huan Xu, Tuo Zhao. ICLR 2020

  
  

• Enhancing Transformation-Based Defenses Against Adversarial Attacks with a Distribution Classifier. Connie Kou, Hwee Kuan Lee, Teck Khim Ng, Ee-Chien Chang. ICLR 2020

• Consistency Regularization for Generative Adversarial Networks. Han Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee. ICLR 2020

• Smoothness and Stability in GANs. Casey Chu, Kentaro Minami, Kenji Fukumizu. ICLR 2020

• Language GANs Falling Short. Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau, Laurent Charlin. ICLR 2020

• Real or Not Real, that is the Question. Yuanbo Xiangli*, Yubin Deng*, Bo Dai*, Chen Change Loy, Dahua Lin. ICLR 2020

• High Fidelity Speech Synthesis with Adversarial Networks. Mikołaj Bińkowski, Jeff Donahue, Sander Dieleman, Aidan Clark, Erich Elsen, Norman Casagrande, Luis C. Cobo, Karen Simonyan. ICLR 2020

 2  

 知识图谱补全 

• You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings. Daniel Ruffinelli, Samuel Broscheit, Rainer Gemulla. ICLR 2020

• Composition-based Multi-Relational Graph Convolutional Networks. Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha Talukdar. ICLR 2020

  
  

• Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings. Hongyu Ren, Weihua Hu, Jure Leskovec. ICLR 2020

• Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph Reasoning. Xiaoran Xu, Wei Feng, Yunsheng Jiang, Xiaohui Xie, Zhiqing Sun, Zhi-Hong Deng. ICLR 2020

 3  

 对话系统

• Asking Clarifying Questions in Open-Domain Information-Seeking Conversations. Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, W.Bruce Croft. SIGIR 2019

  
  

• Estimation–Action–Reflection: Towards Deep Interaction Between Conversational and Recommender Systems. Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, Tat-Seng Chua. WSDM 2020

  
  

• Towards Conversational Search and Recommendation: System Ask, User Respond. Yongfeng Zhang, Xu Chen, Qingyao Ai, Liu Yang, W. Bruce Croft. CIKM 2018

  
  

• Target-Guided Open-Domain Conversation. Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric P. Xing, Zhiting Hu. ACL 2019

  
  

• Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning. Arvind Neelakantan, Semih Yavuz, Sharan Narang, Vishaal Prasad, Ben Goodrich, Daniel Duckworth, Chinnadhurai Sankar, Xifeng Yan. NeurIPS 2019

  
  

• Low-Resource Knowledge-Grounded Dialogue Generation. YXueliang Zhao, Wei Wu, Chongyang Tao, Can Xu, Dongyan Zhao, Rui Yan. ICLR 2020

  
  

 4  

 文本生成

• Plug and Play Language Models: A Simple Approach to Controlled Text Generation. Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, Rosanne Liu. ICLR 2020
  

• On the Weaknesses of Reinforcement Learning for Neural Machine Translation. Lijun Wu, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu. ICLR 2020

  
  

  
  

本期编辑：胡晓璇

---

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”