Update ACL-2019.md

paper lists/ACL-2019.md

@@ -9,6 +9,7 @@
 | When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion | *Elena Voita, Rico Sennrich and Ivan Titov*                  | Context-aware NMT                         | https://arxiv.org/abs/1905.05979 |
 | A Compact and Language-Sensitive Multilingual Translation Method | *Yining Wang, Long Zhou, Jiajun Zhang, Feifei Zhai, Jingfang Xu and Chengqing Zong* | Training               | -                                |
 | Robust Neural Machine Translation with Doubly Adversarial Inputs | *Yong Cheng, Lu Jiang and Wolfgang Macherey*                 | Robustness of NMT                         | https://arxiv.org/abs/1906.02443 |
+| Assessing the Ability of Self-Attention Networks to Learn Word Order | *Baosong Yang, Longyue Wang, Derek F. Wong, Lidia S. Chao, and Zhaopeng Tu* | Robustness of NMT                         | https://arxiv.org/abs/1906.00592 |
 | Shared-Private Bilingual Word Embeddings for Neural Machine Translation | *Xuebo Liu, Derek F. Wong, Yang Liu and Lidia S. Chao, Tong Xiao, Jingbo Zhu*       | Practical Problems in Machine Translation | https://arxiv.org/abs/1906.03100 |
 | Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation | *Viktor Hangya and Alexander Fraser*                         | Low-resource                              | -                                |
 | Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation | *Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita and Tiejun Zhao* | Low-resource                              | -                                |