Fall 2017 CS595I Advanced NLP/ML Seminar

• 09/26:
  • Mahnaz Summer research presentation: Reinforced Pointer-Generator Network for Abstractive Summarization.
  • Xin: FeUdal Networks for Hierarchical Reinforcement Learning, Vezhnevets et al., ICML 2017 https://arxiv.org/pdf/1703.01161.pdf

• 10/03:
  • Vivek: The strange geometry of skip-gram with negative sampling, David Mimno and Laure Thompson, http://aclweb.org/anthology/D17-1307
  • Yijun: Latent Intention Dialogue Models, Wen et al., ICML 2017 https://arxiv.org/pdf/1705.10229.pdf

Word Embeddings

• Mahnaz--Dict2Vec: Learning Word Embeddings using Dictionaires, Julien Tissier and Christophe Gravier and Amaury Habrard http://aclweb.org/anthology/D17-1024
• Mimicking Word Embeddings using Subword RNNs, Yuval Pinter, Robert Guthrie and Jacob Eisenstein http://aclweb.org/anthology/D17-1010

Relational Learning and Reasoning

• Modeling Relational Data with Graph Convolutional Networks, Schlichtkrull et al., https://arxiv.org/pdf/1703.06103.pdf
• A simple neural network module for relational reasoning, Santoro et al., Arxiv https://arxiv.org/abs/1706.01427
• Adversarial Training for Relation Extraction, Yi Wu, David Bamman and Stuart Russell https://people.eecs.berkeley.edu/~russell/papers/emnlp17-relation.pdf
• Adversarial Examples for Evaluating Reading Comprehension Systems Robin Jia and Percy Liang https://arxiv.org/abs/1707.07328

Reinforcement Learning

• FeUdal Networks for Hierarchical Reinforcement Learning, Vezhnevets et al., ICML 2017 https://arxiv.org/pdf/1703.01161.pdf
• Deep reinforcement learning from human preferences, Christiano et al., https://arxiv.org/pdf/1706.03741.pdf
• Deep Reinforcement Learning that Matters, Henderson et al., arxiv https://arxiv.org/pdf/1709.06560.pdf
• Robust Imitation of Diverse Behaviors, Wang et al. 2017, https://arxiv.org/pdf/1707.02747.pdf
• Programmable Agents, Denil et al., https://arxiv.org/pdf/1706.06383v1.pdf
• Expected Policy Gradients, Kamil Ciosek, Shimon Whiteson, https://arxiv.org/abs/1706.05374
• Hindsight Experience Replay, Andrychowicz et al, https://arxiv.org/pdf/1707.01495.pdf
• Reinforcement Learning with Deep Energy-Based Policies Haarnoja et al, ICML 2017 http://proceedings.mlr.press/v70/haarnoja17a/haarnoja17a.pdf
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation, Kulkarni et al., 2016, https://arxiv.org/pdf/1604.06057.pdf
• Modular Multitask Reinforcement Learning with Policy Sketches, Andreas et al., ICML 2017 https://arxiv.org/pdf/1611.01796.pdf
• Device Placement Optimization with Reinforcement Learning, Azalia Mirhoseini et al. https://arxiv.org/pdf/1706.04972.pdf
• Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning, Gu et al., NIPS 2017 https://arxiv.org/abs/1706.00387
• Sequence Level Training with Recurrent Neural Networks https://arxiv.org/pdf/1511.06732.pdf

Learning (General)

• An Overview of Multi-Task Learning in Deep Neural Networks, Sebastian Ruder, https://arxiv.org/abs/1706.05098
• Understanding Black-box Predictions via Influence Functions, Koh and Liang, ICML 2017 Best Paper. https://arxiv.org/pdf/1703.04730.pdf
• The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process, Mei and Eisner, NIPS 2017 https://arxiv.org/pdf/1612.09328.pdf

Generation

• Generating Sentences by Editing Prototypes, Guu et al., arxiv https://arxiv.org/abs/1709.08878
• Multi-Task Video Captioning with Video and Entailment Generation, ACL 2017 Outstanding Paper https://arxiv.org/pdf/1704.07489.pdf
• Adversarial Feature Matching for Text Generation, Zhang et al., ICML 2017 http://proceedings.mlr.press/v70/zhang17b/zhang17b.pdf
• Adversarially Regularized Autoehttp://www.aclweb.org/anthology/D17-1120ncoders for Generating Discrete Structures, Zhao et al., https://arxiv.org/pdf/1706.04223.pdf

Dialog

• Reinforcement learning for spoken dialogue systems: Comparing strengths and weaknesses for practical deployment, DoD workshop, Interspeech 2006 https://pdfs.semanticscholar.org/b75b/e9388fefc44a20ceb40f6e0b916f0bbd7bbe.pdf
• Reinforcement learning for spoken dialogue systems, Singh et al., NIPS 2000 http://papers.nips.cc/paper/1775-reinforcement-learning-for-spoken-dialogue-systems.pdf
• Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management, Su et al., SIGDIAL 2017 https://arxiv.org/pdf/1707.00130.pdf
• Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning, Peng et al., EMNLP 2017. https://arxiv.org/abs/1704.03084
• Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog, Kottur et al., EMNLP best paper, https://arxiv.org/pdf/1706.08502.pdf
• A Deep Reinforcement Learning Chatbot, Serban et al., https://arxiv.org/pdf/1709.02349.pdf
• Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses, ACL 2017 Outstanding Paper http://aclweb.org/anthology/P/P17/P17-1103.pdf

NLP for Computational Social Science

• Analyzing Language in Fake News and Political Fact-Checking, Hannah Rashkin, Eunsol Choi, Jin Yea Jang, Svitlana Volkova and Yejin Choi https://www.cs.jhu.edu/~svitlana/papers/RCYVC_EMNLP2017.pdf
• Human Centered NLP with User Factor Adaptation. Veronica Lynn, Youngseo Son, Vivek Kulkarni, Niranjan Balasubramanian, H Andrew Schwartz, http://www.aclweb.org/anthology/D17-1120