alainloisel / rl4nlp

Reinforcement learning for natural language processing reading group

RL4NLP Reading Group (Spring 2017)

• Location: CSE 203

Schedule

1. RL Basic and MDP

• Yangfeng
• Time: April 17, Monday, 4:30 - 5:30 PM
• Reading: Reinforcement Learning: An Introduction Chap 01 and 03
• Notes: Chap 01 and Chap 03

2. Dynamic Programming and Monte Carlo Methods

• Chenhao
• Time: April 24, Monday, 4:30 - 5:30 PM
• Reading: Reinforcement Learning: An Introduction Chap 04 and 05

3. Policy Gradient Methods

• Ji
• Time: May 1, Monday, 4:30 - 5:30 PM
• Reading: Reinforcement Learning: An Introduction Chap 13

4. POS tagging and Syntactic Parsing

• Yijia
• Time: May 8, Monday, 4:30 - 5:30 PM
• Suggested reading:
  • EACL imitation learning tutorail
  • DAGGER
  • LOLS
  • A Dynamic Oracle for Arc-Eager Dependency Parsing
  • Noise Reduction and Targeted Exploration in Imitation Learning for Abstract Meaning Representation Parsing

5. Information Extraction

• Colin
• Time: May 15, Monday, 4:30 - 5:30 PM
• Suggested reading: some papers from Regina's group
  • Learning to Win by Reading Manuals in a Monte-Carlo Framework
  • Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning

6. Machine Translation and Language Modeling

• Max
• Time: May 22, Monday, 4:30 - 5:30 PM
• Suggested reading:
  • Don’t Until the Final Verb Wait: Reinforcement Learning for Simultaneous Machine Translation
  • Dual Learning for Machine Translation

7. Summarization and Question Answering

• Mandar
• Time: Jun 5, Monday, 4:30 - 5:30 PM
• Suggested reading:
  • A Deep Reinforced Model for Abstractive Summarization
  • Coarse-to-Fine Question Answering for Long Documents