EMNLP Paper Selective Reading

Sep. 26, 2018

This week’s reading list is below:

• Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing. NAACL 2018.
• One-Shot Relational Learning for Knowledge Graphs. NAACL 2018.
  • Presenter: Guanlin Li
• A Stable and Effective Learning Strategy for Trainable Greedy Decoding. CVPR 2018
• Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter, 2015.
  • Presenter: Qian Wang

Oct. 15, 2018

This week’s reading list is below:

• Meta-Learning for Low-Resource Neural Machine Translation, EMNLP 2018.
• Contextual Parameter Generation for Universal Neural Machine Translation, EMNLP 2018.
• Large Margin Neural Language Model, EMNLP 2018.
  • Presenter: Xintong Li
• Unsupervised Statistical Machine Translation, EMNLP 2018.
• Phrase-Based & Neural Unsupervised Machine Translation, EMNLP 2018.
  • Presenter: Huayang Li

Oct. 29, 2018

This week’s reading list is below:

Two papers about robust optimization:

• Fairness Without Demographics in Repeated Loss Minimization, ICML 2018 Best Paper Honarable Metioned. Percy Liang and John Duchi’s group.
• Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences, and code, NIPS 2016. John Duchi’s group.

One paper about doing NAS with efficient training (x1000 speedup compared to other NASs):

• Efficient Neural Architecture Search via Parameter Sharing, and slides. ICML 2018.

---