Home - RamonYeung/ZJU-NLP GitHub Wiki

Paper List

Here are our reading list for multiple topics including:

Semantic Parsing / Sequence to Logical Form

  • Semantic Parsing with Neural Hybrid Trees [2017-AAAI]

  • Neural Architectures for Multilingual Semantic Parsing [2017-ACL]

  • Transfer Learning for Neural Semantic Parsing [2017-ACL]

  • Neural Semantic Parsing with Type Constraints for Semi-structured Tables [2017-EMNLP]

  • Seq2sql Generating Structured Queries from Natural Language using Reinforcement Learning [2017]

  • An Encoder-Decoder Framework Translating Natural Language to Database Queries [2017]

  • Learning an Executable Neural Semantic Parser [2017]

  • SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning [2018]

  • Learning a Neural Semantic Parser from User Feedback [2017-ACL]

  • Data Recombination for Neural Semantic Parsing [2016-ACL]

  • Sequence-based Structured Prediction for Semantic Parsing [2016-ACL]

  • Semantic Parsing with Semi-Supervised Sequential Autoencoders [2016-EMNLP]

  • Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision [2017-ACL]

  • Language to Logical Form with Neural Attention [2016-ACL]

Reinforcement Learning

  • From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood [2017]

  • Prioritized Experience Replay [2015]

  • Dueling Network Architectures for Deep Reinforcement Learning [2015]

Classic Papers

  • Online Q-learning using Connectionist Systems (Known as Sarsa) [1994]

  • Policy Gradient Methods for Reinforcement Learning with Function Approximation [2000-NIPS]

  • A Natural Policy Gradient [2002-NIPS]

  • Q Learning [1992]

  • Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning (Known as REINFORCE) [1992]

  • Neuronlike adaptive elements that can solve difficult learning control problems (Known as Actor-Critic) [1983]

  • Learning to Predict by the Methods of Temporal Differences (Known as TD Learning) [1988]

  • Human-level Control Through Deep Reinforcement Learning (Known as DQN) [2015-Nature]

  • Double Reinforcement Learning with Double Q-learning (Known as Double DQN, DDQN) [2016-AAAI]

  • Deterministic policy gradient algorithms (Known as DPG) [2014-ICML]

  • Continuous control with deep reinforcement learning (Known as DDPG) [2015-ICLR]

  • Asynchronous Methods for Deep Reinforcement Learning (Known as A3C) [2016]

Fundamental Theories

  • Convergence of Stochastic Iterative Dynamic Programming Algorithms (Learning Rate Schedule) [1994-NIPS]

  • Reinforcement Learning for Robots Using Neural Networks (Known as Experience Replay) [1993]

  • On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient [2011-NIPS]

Gradient Estimation

  • Stochastic Gradient Estimation [2006]

  • Gradient Estimation using Stochastic Computation Graphs [2015-NIPS]

  • Infinite Horizon Policy Gradient Estimation (Known as GPOMDP_) [2011-JAIR]

  • Policy Gradient Methods for Robotics [2006-IROS]

Variance Reduction

  • Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning [2004-JMLR]

Paper List (Unsorted)

Applications / Applied Data Science