12 bib

bibliography.bib

@@ -5569,6 +5569,7 @@ author    = {Yoshua Bengio and
 
 @article{DBLP:journals/corr/abs-2004-05150,
   author    = {Iz Beltagy and
+  author    = {Iz Beltagy and
                Matthew E. Peters and
                Arman Cohan},
   title     = {Longformer: The Long-Document Transformer},
@@ -5721,10 +5722,16 @@ author    = {Yoshua Bengio and
 	year={2019}
 }
 @inproceedings{Yang2018ModelingLF,
-	title={Modeling Localness for Self-Attention Networks},
-	author={Baosong Yang and Zhaopeng Tu and Derek F. Wong and Fandong Meng and Lidia S. Chao and T. Zhang},
-	publisher={Conference on Empirical Methods in Natural Language Processing},
-	year={2018}
+	author    = {Baosong Yang and
+               Zhaopeng Tu and
+               Derek F. Wong and
+               Fandong Meng and
+               Lidia S. Chao and
+               Tong Zhang},
+  title     = {Modeling Localness for Self-Attention Networks},
+  pages     = {4449--4458},
+  publisher = {Association for Computational Linguistics},
+  year      = {2018}
 }
 @inproceedings{DBLP:journals/corr/abs-1904-03107,
 	author = {Baosong Yang and
@@ -5745,10 +5752,16 @@ author    = {Yoshua Bengio and
   volume={abs/2002.06714}
 }
 @inproceedings{Bapna2018TrainingDN,
-  title={Training Deeper Neural Machine Translation Models with Transparent Attention},
-  author={Ankur Bapna and M. Chen and Orhan Firat and Yuan Cao and Y. Wu},
-  publisher={Conference on Empirical Methods in Natural Language Processing},
-  year={2018}
+  author    = {Ankur Bapna and
+               Mia Xu Chen and
+               Orhan Firat and
+               Yuan Cao and
+               Yonghui Wu},
+  title     = {Training Deeper Neural Machine Translation Models with Transparent
+               Attention},
+  pages     = {3028--3033},
+  publisher = {Association for Computational Linguistics},
+  year      = {2018}
 }
 @inproceedings{Dou2018ExploitingDR,
    author    = {Zi-Yi Dou and
@@ -5788,18 +5801,32 @@ author    = {Yoshua Bengio and
 }
 
 @inproceedings{Vaswani2018Tensor2TensorFN,
-  title={Tensor2Tensor for Neural Machine Translation},
-  author={Ashish Vaswani and S. Bengio and E. Brevdo and F. Chollet and Aidan N. Gomez and S. Gouws and Llion Jones and L. Kaiser and Nal Kalchbrenner and Niki Parmar and Ryan Sepassi and Noam Shazeer and Jakob Uszkoreit},
-  booktitle={American Mobile Telecommunications Association },
-  year={2018}
+   author    = {Ashish Vaswani and
+               Samy Bengio and
+               Eugene Brevdo and
+               Fran{\c{c}}ois Chollet and
+               Aidan N. Gomez and
+               Stephan Gouws and
+               Llion Jones and
+               Lukasz Kaiser and
+               Nal Kalchbrenner and
+               Niki Parmar and
+               Ryan Sepassi and
+               Noam Shazeer and
+               Jakob Uszkoreit},
+  title     = {Tensor2Tensor for Neural Machine Translation},
+  pages     = {193--199},
+  publisher = {Association for Machine Translation in the Americas},
+  year      = {2018}
 }
 
 @article{Kitaev2020ReformerTE,
-  title={Reformer: The Efficient Transformer},
-  author={Nikita Kitaev and L. Kaiser and Anselm Levskaya},
-  journal={ArXiv},
-  year={2020},
-  volume={abs/2001.04451}
+  author    = {Nikita Kitaev and
+               Lukasz Kaiser and
+               Anselm Levskaya},
+  title     = {Reformer: The Efficient Transformer},
+  publisher = {OpenReview.net},
+  year      = {2020}
 }
 
 @article{Lin2020WeightDT,