Schedule

Friday July 20, Room 211


09:00–09:10        Welcome and Opening Remarks 
                   Findings of the Second Workshop on Neural Machine Translation and Generation 
                   Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda 

09:10–10:00        Keynote 1:  Real-time High-quality Neural MT Decoding on Mobile Devices
                   Jacob Devlin

10:00–10:30        Shared Task Overview 

10:30–11:00        Coffee Break 

11:00–11:30        Marian: Fast Neural Machine Translation in C++ 

11:30–12:20        Keynote 2:  Why the Time Is Ripe for Discourse in Machine Translation
                   Rico Sennrich 

12:20–13:20        Lunch Break 

13:20–13:50        Best Paper Session

                   André Martins 
                   

14:40–15:30        Keynote 4:  Towards Flexible but Controllable Language Generation  
                   Yulia Tsvetkov 

15:30–16:00        Coffee Break

16:00–17:30        Poster Session 

A Shared Attention Mechanism for Interpretation of Neural Automatic Post-Editing Systems 
Inigo Jauregi Unanue, Ehsan Zare Borzeshi and Massimo Piccardi 

Iterative Back-Translation for Neural Machine Translation 
Vu Cong Duy Hoang, Philipp Koehn, Gholamreza Haffari and Trevor Cohn 

Inducing Grammars with and for Neural Machine Translation 
Yonatan Bisk and Ke Tran 

Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation 
Huda Khayrallah, Brian Thompson, Kevin Duh and Philipp Koehn 

Controllable Abstractive Summarization 
Angela Fan, David Grangier and Michael Auli 

Enhancement of Encoder and Attention Using Target Monolingual Corpora in Neural Machine Translation 
Kenji Imamura, Atsushi Fujita and Eiichirō Sumita 

Document-Level Adaptation for Neural Machine Translation 
Sachith Sri Ram Kothur, Rebecca Knowles and Philipp Koehn 

On the Impact of Various Types of Noise on Neural Machine Translation 
Huda Khayrallah and Philipp Koehn 

Bi-Directional Neural Machine Translation with Synthetic Parallel Data 
Xing Niu, Michael Denkowski and Marine Carpuat 

Multi-Source Neural Machine Translation with Missing Data 
Yuta Nishimura, Katsuhito Sudoh, Graham Neubig and Satoshi Nakamura 

Towards one-shot learning for rare-word translation with external experts 
Ngoc-Quan Pham, Jan Niehues and Alexander Waibel

NICT Self-Training Approach to Neural Machine Translation at NMT-2018 
Kenji Imamura and Eiichirō Sumita 

Fast Neural Machine Translation Implementation 
Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa and Kenneth Heafield 

OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU 
Jean Senellart, Dakun Zhang, Bo WANG, Guillaume KLEIN, Jean-Pierre Ramatchandirin, Josep Crego and Alexander Rush 

Marian: Cost-effective High-Quality Neural Machine Translation in C++ 
Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz and Anthony Aue 

On Individual Neurons in Neural Machine Translation 
D. Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi and James Glass 

Parameter Sharing Strategies in Neural Machine Translation 
Sébastien Jean, Stanislas Lauly and Kyunghyun Cho 

Modeling Latent Sentence Structure in Neural Machine Translation 
Joost Bastings, Wilker Aziz, Ivan Titov and Khalil Simaan 

Extreme Adaptation for Personalized Neural Machine Translation 
Paul Michel and Graham Neubig 

Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks 
Diego Marcheggiani, Joost Bastings and Ivan Titov 

17:30–17:40        Closing Remarks
Comments