合并分支 'zengxin' 到 'caorunzhe'

Zengxin 查看合并请求 !655

合并分支 'zengxin' 到 'caorunzhe'
Zengxin 查看合并请求 !655
65f8fd03 · zengxin · 29da486c · 017c3ecb · 65f8fd03
Commit 65f8fd03 authored Dec 21, 2020 by zengxin
--- a/bibliography.bib
+++ b/bibliography.bib
@@ -4387,32 +4387,32 @@ year = {2012}
  publisher = {Annual Meeting of the Association for Computational Linguistics},
  year      = {2013}
 }
-@article{HochreiterThe,
+@inproceedings{HochreiterThe,
  author    = {Sepp Hochreiter},
  title     = {The Vanishing Gradient Problem During Learning Recurrent Neural Nets
               and Problem Solutions},
-  journal   = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},
+  publisher   = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},
  volume    = {6},
  number    = {2},
  pages     = {107--116},
  year      = {1998}
 }
-@article{BENGIO1994Learning,
+@inproceedings{BENGIO1994Learning,
 author    = {Yoshua Bengio and
               Patrice Y. Simard and
               Paolo Frasconi},
  title     = {Learning long-term dependencies with gradient descent is difficult},
-  journal   = {IEEE Transportation Neural Networks},
+  publisher   = {IEEE Transportation Neural Networks},
  volume    = {5},
  number    = {2},
  pages     = {157--166},
  year      = {1994}
 }
-@article{StahlbergNeural,
+@inproceedings{StahlbergNeural,
  title={Neural Machine Translation: A Review},
  author={Felix Stahlberg},
-  journal={Journal of Artificial Intelligence Research},
+  publisher={Journal of Artificial Intelligence Research},
  year={2020},
  volume={69},
  pages={343-418}
@@ -4427,7 +4427,7 @@ author    = {Yoshua Bengio and
  publisher = {Annual Meeting of the Association for Computational Linguistics},
  year      = {2016}
 }
-@article{Hassan2018AchievingHP,
+@inproceedings{Hassan2018AchievingHP,
  author    = {Hany Hassan and
               Anthony Aue and
               Chang Chen and
@@ -4453,7 +4453,7 @@ author    = {Yoshua Bengio and
               Zhirui Zhang and
               Ming Zhou},
  title     = {Achieving Human Parity on Automatic Chinese to English News Translation},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1803.05567},
  year      = {2018},
 }
@@ -4481,14 +4481,14 @@ author    = {Yoshua Bengio and
  publisher = {AAAI Conference on Artificial Intelligence},
  year      = {2020}
 }
-@article{HochreiterLong,
+@inproceedings{HochreiterLong,
  author = {Hochreiter, Sepp and Schmidhuber, Jürgen},
  year = {1997},
  month = {12},
  pages = {1735-80},
  title = {Long Short-term Memory},
  volume = {9},
-  journal = {Neural Computation}
+  publisher = {Neural Computation}
 }
 @inproceedings{Cho2014Learning,
  author    = {Kyunghyun Cho and
@@ -4580,12 +4580,12 @@ author    = {Yoshua Bengio and
  pages     = {1538--1548},
  year      = {2019}
 }
-@article{Lei2017TrainingRA,
+@inproceedings{Lei2017TrainingRA,
  author    = {Tao Lei and
               Yu Zhang and
               Yoav Artzi},
  title     = {Training RNNs as Fast as CNNs},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1709.02755},
  year      = {2017}
 }
@@ -4693,15 +4693,15 @@ author    = {Yoshua Bengio and
  pages     = {4772--4777},
  year      = {2018}
 }
-@article{DBLP:journals/corr/ZhangZ16c,
+@inproceedings{DBLP:journals/corr/ZhangZ16c,
  author    = {Jiajun Zhang and
               Chengqing Zong},
  title     = {Bridging Neural Machine Translation and Bilingual Dictionaries},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1610.07272},
  year      = {2016}
 }
-@article{Dai2019TransformerXLAL,
+@inproceedings{Dai2019TransformerXLAL,
  author    = {Zihang Dai and
               Zhilin Yang and
               Yiming Yang and
@@ -4709,7 +4709,7 @@ author    = {Yoshua Bengio and
               Quoc V. Le and
               Ruslan Salakhutdinov},
  title     = {Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context},
-  journal   = {Annual Meeting of the Association for Computational Linguistics},
+  publisher   = {Annual Meeting of the Association for Computational Linguistics},
  pages     = {2978--2988},
  year      = {2019}
 }
@@ -4746,7 +4746,7 @@ author    = {Yoshua Bengio and
  pages     = {1264--1274},
  year      = {2018}
 }
-@article{DBLP:journals/corr/abs-1906-00532,
+@inproceedings{DBLP:journals/corr/abs-1906-00532,
  author    = {Aishwarya Bhandare and
               Vamsi Sripathi and
               Deepthi Karkada and
@@ -4756,7 +4756,7 @@ author    = {Yoshua Bengio and
               Vikram Saletore},
  title     = {Efficient 8-Bit Quantization of Transformer Neural Machine Language
               Translation Model},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1906.00532},
  year      = {2019}
 }
@@ -4791,12 +4791,12 @@ author    = {Yoshua Bengio and
  publisher = {Annual Meeting of the Association for Computational Linguistics},
  year      = {2017}
 }
-@article{Hinton2015Distilling,
+@inproceedings{Hinton2015Distilling,
  author    = {Geoffrey Hinton and
               Oriol Vinyals and
               Jeffrey Dean},
  title     = {Distilling the Knowledge in a Neural Network},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1503.02531},
  year      = {2015}
 }
@@ -4827,10 +4827,10 @@ author    = {Yoshua Bengio and
  publisher = {Conference on Empirical Methods in Natural Language Processing},
  year      = {2016}
 }
-@article{Akaike1969autoregressive,
+@inproceedings{Akaike1969autoregressive,
  author    = {Hirotugu Akaike},
  title     = {Fitting autoregressive models for prediction},
-  journal   = {Annals of the institute of Statistical Mathematics},
+  publisher   = {Annals of the institute of Statistical Mathematics},
  volume    = {21(1)},
  year      = {2015},
  pages     = {243--247},
@@ -4958,14 +4958,14 @@ author    = {Yoshua Bengio and
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 %%%%% chapter 11------------------------------------------------------
-@article{DBLP:journals/pami/RenHG017,
+@inproceedings{DBLP:journals/pami/RenHG017,
  author    = {Shaoqing Ren and
               Kaiming He and
               Ross Girshick and
               Jian Sun},
  title     = {Faster {R-CNN:} Towards Real-Time Object Detection with Region Proposal
               Networks},
-  journal   = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence},
+  publisher   = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence},
  volume    = {39},
  number    = {6},
  pages     = {1137--1149},
@@ -5101,10 +5101,10 @@ author    = {Yoshua Bengio and
  year      = {2017}
 }
-@article{2011Natural,
+@inproceedings{2011Natural,
  title={Natural Language Processing (almost) from Scratch},
  author={ Collobert, Ronan  and  Weston, Jason  and Bottou, Léon and  Karlen, Michael  and  Kavukcuoglu, Koray  and  Kuksa, Pavel },
-  journal={Journal of Machine Learning Research},
+  publisher={Journal of Machine Learning Research},
  volume={12},
  number={1},
  pages={2493-2537},
@@ -5171,16 +5171,16 @@ author    = {Yoshua Bengio and
  year      = {2015}
 }
-@article{StahlbergNeural,
+@inproceedings{StahlbergNeural,
  title={Neural Machine Translation: A Review},
  author={Felix Stahlberg},
-  journal={Journal of Artificial Intelligence Research},
+  publisher={Journal of Artificial Intelligence Research},
  year={2020},
  volume={69},
  pages={343-418}
 }
-@article{Sennrich2016ImprovingNM,
+@inproceedings{Sennrich2016ImprovingNM,
  author    = {Rico Sennrich and
               Barry Haddow and
               Alexandra Birch},
@@ -5198,27 +5198,27 @@ author    = {Yoshua Bengio and
  year      = {2015}
 }
-@article{Waibel1989PhonemeRU,
+@inproceedings{Waibel1989PhonemeRU,
  title={Phoneme recognition using time-delay neural networks},
  author={Alexander Waibel and Toshiyuki Hanazawa and Geoffrey Hinton and Kiyohiro Shikano and Kevin J. Lang},
-  journal={IEEE Transactions on Acoustics, Speech, and Signal Processing},
+  publisher={IEEE Transactions on Acoustics, Speech, and Signal Processing},
  year={1989},
  volume={37},
  pages={328-339}
 }
-@article{LeCun1989BackpropagationAT,
+@inproceedings{LeCun1989BackpropagationAT,
  title={Backpropagation Applied to Handwritten Zip Code Recognition},
  author={Yann Lecun and Bernhard Boser and John Denker and Don Henderson and Richard E.Howard and Wayne E. Hubbard and Larry Jackel},
-  journal={Neural Computation},
+  publisher={Neural Computation},
  year={1989},
  volume={1},
  pages={541-551}
 }
-@article{726791,
+@inproceedings{726791,
  author={Yann {Lecun} and Leon {Bottou} and Yoshua {Bengio} and Patrick {Haffner}},
-  journal={Proceedings of the IEEE}, 
+  publisher={Proceedings of the IEEE}, 
  title={Gradient-based learning applied to document recognition}, 
  year={1998},
  volume={86},
@@ -5248,18 +5248,18 @@ author    = {Yoshua Bengio and
  year      = {2017}
 }
-@article{Girshick2015FastR,
+@inproceedings{Girshick2015FastR,
  title={Fast R-CNN},
  author={Ross Girshick},
-  journal={International Conference on Computer Vision},
+  publisher={International Conference on Computer Vision},
  year={2015},
  pages={1440-1448}
 }
-@article{He2020MaskR,
+@inproceedings{He2020MaskR,
  title={Mask R-CNN},
  author={Kaiming He and Georgia Gkioxari and Piotr Doll{\'a}r and Ross B. Girshick},
-  journal={International Conference on Computer Vision},
+  publisher={International Conference on Computer Vision},
  pages={2961--2969},
  year={2017}
 }
@@ -5336,12 +5336,12 @@ author    = {Yoshua Bengio and
  year      = {2017}
 }
-@article{Kaiser2018DepthwiseSC,
+@inproceedings{Kaiser2018DepthwiseSC,
  title={Depthwise Separable Convolutions for Neural Machine Translation},
  author    = {Lukasz Kaiser and
               Aidan N. Gomez and
               Fran{\c{c}}ois Chollet},
-  journal = {International Conference on Learning Representations},
+  publisher = {International Conference on Learning Representations},
  year={2018},
 }
@@ -5365,7 +5365,7 @@ author    = {Yoshua Bengio and
  year      = {2013}
 }
-@article{Wu2016GooglesNM,
+@inproceedings{Wu2016GooglesNM,
  title={Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
  author    = {Yonghui Wu and
               Mike Schuster and
@@ -5398,7 +5398,7 @@ author    = {Yoshua Bengio and
               Greg Corrado and
               Macduff Hughes and
               Jeffrey Dean},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  year={2016},
  volume={abs/1609.08144}
 }
@@ -5444,32 +5444,32 @@ author    = {Yoshua Bengio and
  year={2013}
 }
-@article{Bengio2013AdvancesIO,
+@inproceedings{Bengio2013AdvancesIO,
  title={Advances in optimizing recurrent networks},
  author={Yoshua Bengio and Nicolas Boulanger-Lewandowski and Razvan Pascanu},
-  journal={IEEE Transactions on Acoustics, Speech, and Signal Processing},
+  publisher={IEEE Transactions on Acoustics, Speech, and Signal Processing},
  year={2013},
  pages={8624-8628}
 }
-@article{JMLR:v15:srivastava14a,
+@inproceedings{JMLR:v15:srivastava14a,
  author  = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
  title   = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
-  journal = {Journal of Machine Learning Research},
+  publisher = {Journal of Machine Learning Research},
  year    = {2014},
  volume  = {15},
  pages   = {1929-1958},
 }
-@article{Chollet2017XceptionDL,
+@inproceedings{Chollet2017XceptionDL,
  title={Xception: Deep Learning with Depthwise Separable Convolutions},
  author    = {Fran{\c{c}}ois Chollet},
-  journal={IEEE Conference on Computer Vision and Pattern Recognition},
+  publisher={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2017},
  pages={1800-1807}
 }
-@article{Howard2017MobileNetsEC,
+@inproceedings{Howard2017MobileNetsEC,
  title={MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
  author    = {Andrew Howard and
               Menglong Zhu and
@@ -5483,17 +5483,17 @@ author    = {Yoshua Bengio and
  year={2017},
 }
-@article{sifre2014rigid,
+@inproceedings{sifre2014rigid,
  title={Rigid-motion scattering for image classification},
  author={Sifre, Laurent and Mallat, St{\'e}phane},
  year={2014},
-  journal={Citeseer}
+  publisher={Citeseer}
 }
-@article{Taigman2014DeepFaceCT,
+@inproceedings{Taigman2014DeepFaceCT,
  title={DeepFace: Closing the Gap to Human-Level Performance in Face Verification},
  author={Yaniv Taigman and Ming Yang and Marc'Aurelio Ranzato and Lior Wolf},
-  journal={IEEE Conference on Computer Vision and Pattern Recognition},
+  publisher={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={1701-1708}
 }
@@ -5511,7 +5511,7 @@ author    = {Yoshua Bengio and
  year={2015}
 }
-@article{Chen2020DynamicCA,
+@inproceedings{Chen2020DynamicCA,
  title={Dynamic Convolution: Attention Over Convolution Kernels},
  author    = {Yinpeng Chen and
               Xiyang Dai and
@@ -5519,7 +5519,7 @@ author    = {Yoshua Bengio and
               Dongdong Chen and
               Lu Yuan and
               Zicheng Liu},
-  journal = {IEEE Conference on Computer Vision and Pattern Recognition},
+  publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
  year={2020},
  pages={11027-11036}
 }
@@ -5579,7 +5579,7 @@ author    = {Yoshua Bengio and
  year      = {2018}
 }
-@article{DBLP:journals/corr/abs-1802-05751,
+@inproceedings{DBLP:journals/corr/abs-1802-05751,
  author    = {Niki Parmar and
               Ashish Vaswani and
               Jakob Uszkoreit and
@@ -5587,7 +5587,7 @@ author    = {Yoshua Bengio and
               Noam Shazeer and
               Alexander Ku},
  title     = {Image Transformer},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1802.05751},
  year      = {2018}
 }
@@ -5612,17 +5612,17 @@ author    = {Yoshua Bengio and
  year      = {2020}
 }
-@article{DBLP:journals/corr/abs-2004-05150,
+@inproceedings{DBLP:journals/corr/abs-2004-05150,
  author    = {Iz Beltagy and
               Matthew E. Peters and
               Arman Cohan},
  title     = {Longformer: The Long-Document Transformer},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/2004.05150},
  year      = {2020}
 }
-@article{DBLP:journals/corr/abs-2005-00743,
+@inproceedings{DBLP:journals/corr/abs-2005-00743,
  author    = {Yi Tay and
               Dara Bahri and
               Donald Metzler and
@@ -5630,7 +5630,7 @@ author    = {Yoshua Bengio and
               Zhe Zhao and
               Che Zheng},
  title     = {Synthesizer: Rethinking Self-Attention in Transformer Models},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/2005.00743},
  year      = {2020}
 }
@@ -5691,10 +5691,10 @@ author    = {Yoshua Bengio and
  pages     = {770--778},
  year      = {2016},
 }
-@article{JMLR:v15:srivastava14a,
+@inproceedings{JMLR:v15:srivastava14a,
  author  = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
  title   = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
-  journal = {Journal of Machine Learning Research},
+  publisher = {Journal of Machine Learning Research},
  year    = {2014},
  volume  = {15},
  pages   = {1929-1958},
@@ -5719,12 +5719,12 @@ author    = {Yoshua Bengio and
  pages     = {1789--1798},
  year      = {2018},
 }
-@article{DBLP:journals/corr/CourbariauxB16,
+@inproceedings{DBLP:journals/corr/CourbariauxB16,
  author    = {Matthieu Courbariaux and
               Yoshua Bengio},
  title     = {BinaryNet: Training Deep Neural Networks with Weights and Activations
               Constrained to +1 or -1},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1602.02830},
  year      = {2016},
 }
@@ -5751,10 +5751,10 @@ author    = {Yoshua Bengio and
  publisher = {Annual Meeting of the Association for Computational Linguistics},
  year      = {2019}
 }
-@article{Liu2020LearningTE,
+@inproceedings{Liu2020LearningTE,
 	title={Learning to Encode Position for Transformer with Continuous Dynamical Model},
 	author={Xuanqing Liu and Hsiang-Fu Yu and Inderjit Dhillon and Cho-Jui Hsieh},
-	journal={ArXiv},
+	publisher={ArXiv},
 	year={2020},
 	volume={abs/2003.09229}
 }
@@ -5787,10 +5787,10 @@ author    = {Yoshua Bengio and
 	publisher = {Annual Meeting of the Association for Computational Linguistics},
 	year = {2019},
 }
-@article{Wang2018MultilayerRF,
+@inproceedings{Wang2018MultilayerRF,
  title={Multi-layer Representation Fusion for Neural Machine Translation},
  author={Qiang Wang and Fuxue Li and Tong Xiao and Yanyang Li and Yinqiao Li and Jingbo Zhu},
-  journal={International Conference on Computational Linguistics},
+  publisher={International Conference on Computational Linguistics},
  year={2018},
  volume={abs/2002.06714}
 }
@@ -5863,27 +5863,27 @@ author    = {Yoshua Bengio and
  year      = {2018}
 }
-@article{Kitaev2020ReformerTE,
+@inproceedings{Kitaev2020ReformerTE,
  author    = {Nikita Kitaev and
               Lukasz Kaiser and
               Anselm Levskaya},
  title     = {Reformer: The Efficient Transformer},
-  journal = {International Conference on Learning Representations},
+  publisher = {International Conference on Learning Representations},
  year      = {2020}
 }
-@article{Lin2020WeightDT,
+@inproceedings{Lin2020WeightDT,
  title={Weight Distillation: Transferring the Knowledge in Neural Network Parameters},
  author={Ye Lin and Yanyang Li and Ziyang Wang and Bei Li and Quan Du and Tong Xiao and Jingbo Zhu},
-  journal={ArXiv},
+  publisher={ArXiv},
  year={2020},
  volume={abs/2009.09152}
 }
-@article{li2020shallow,
+@inproceedings{li2020shallow,
  title={Shallow-to-Deep Training for Neural Machine Translation},
  author={Li, Bei and Wang, Ziyang and Liu, Hui and Jiang, Yufan and Du, Quan and Xiao, Tong and Wang, Huizhen and Zhu, Jingbo},
-  journal={Conference on Empirical Methods in Natural Language Processing},
+  publisher={Conference on Empirical Methods in Natural Language Processing},
  year={2020}
 }
 %%%%% chapter 12------------------------------------------------------
@@ -14049,50 +14049,50 @@ author    = {Zhuang Liu and
  year      = {2017}
 }
-@article{DBLP:journals/corr/abs-1805-01553,
+@inproceedings{DBLP:journals/corr/abs-1805-01553,
  author    = {Tsz Kin Lam and
               Julia Kreutzer and
               Stefan Riezler},
  title     = {A Reinforcement Learning Approach to Interactive-Predictive Neural
               Machine Translation},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1805.01553},
  year      = {2018}
 }
-@article{DBLP:journals/mt/DomingoPC17,
+@inproceedings{DBLP:journals/mt/DomingoPC17,
  author    = {Miguel Domingo and
               {\'{A}}lvaro Peris and
               Francisco Casacuberta},
  title     = {Segment-based interactive-predictive machine translation},
-  journal   = {Machine Translation},
+  publisher   = {Machine Translation},
  volume    = {31},
  number    = {4},
  pages     = {163--185},
  year      = {2017}
 }
-@article{Peris2017InteractiveNM,
+@inproceedings{Peris2017InteractiveNM,
  title={Interactive neural machine translation},
  author={{\'A}lvaro Peris and Miguel Domingo and F. Casacuberta},
-  journal={Computer Speech and Language},
+  publisher={Computer Speech and Language},
  year={2017},
  volume={45},
  pages={201-220}
 }
-@article{DBLP:journals/csl/PerisC19,
+@inproceedings{DBLP:journals/csl/PerisC19,
  author    = {{\'{A}}lvaro Peris and
               Francisco Casacuberta},
  title     = {Online learning for effort reduction in interactive neural machine
               translation},
-  journal   = {Computer Speech Language},
+  publisher   = {Computer Speech Language},
  volume    = {58},
  pages     = {98--126},
  year      = {2019}
 }
-@article{DBLP:journals/coling/BarrachinaBCCCKLNTVV09,
+@inproceedings{DBLP:journals/coling/BarrachinaBCCCKLNTVV09,
  author    = {Sergio Barrachina and
               Oliver Bender and
               Francisco Casacuberta and
@@ -14105,7 +14105,7 @@ author    = {Zhuang Liu and
               Enrique Vidal and
               Juan Miguel Vilar},
  title     = {Statistical Approaches to Computer-Assisted Translation},
-  journal   = {Computer Linguistics},
+  publisher   = {Computer Linguistics},
  volume    = {35},
  number    = {1},
  pages     = {3--28},
@@ -14131,14 +14131,14 @@ author    = {Zhuang Liu and
  year      = {2016}
 }
-@article{DBLP:journals/corr/abs-2010-05680,
+@inproceedings{DBLP:journals/corr/abs-2010-05680,
  author    = {Jiarui Fang and
               Yang Yu and
               Chengduo Zhao and
               Jie Zhou},
  title     = {TurboTransformers: An Efficient {GPU} Serving System For Transformer
               Models},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/2010.05680},
  year      = {2020}
 }
@@ -14155,13 +14155,13 @@ author    = {Zhuang Liu and
  year      = {2018}
 }
-@article{DBLP:journals/corr/BolukbasiWDS17,
+@inproceedings{DBLP:journals/corr/BolukbasiWDS17,
  author    = {Tolga Bolukbasi and
               Joseph Wang and
               Ofer Dekel and
               Venkatesh Saligrama},
  title     = {Adaptive Neural Networks for Fast Test-Time Prediction},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1702.07811},
  year      = {2017}
 }
@@ -14188,13 +14188,13 @@ author    = {Zhuang Liu and
  year      = {2020}
 }
-@article{DBLP:journals/corr/abs-1912-00567,
+@inproceedings{DBLP:journals/corr/abs-1912-00567,
  author    = {Tao Wang and
               Shaohui Kuang and
               Deyi Xiong and
               Ant{\'{o}}nio Branco},
  title     = {Merging External Bilingual Pairs into Neural Machine Translation},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1912.00567},
  year      = {2019}
 }
@@ -14292,20 +14292,20 @@ author    = {Zhuang Liu and
  year      = {2018}
 }
-@article{barone2017regularization,
+@inproceedings{barone2017regularization,
  title={Regularization techniques for fine-tuning in neural machine translation},
  author={Barone, Antonio Valerio Miceli and Haddow, Barry and Germann, Ulrich and Sennrich, Rico},
-  journal={arXiv preprint arXiv:1707.09920},
+  publisher={arXiv preprint arXiv:1707.09920},
  year={2017}
 }
-@article{DBLP:journals/corr/ChuDK17,
+@inproceedings{DBLP:journals/corr/ChuDK17,
  author    = {Chenhui Chu and
               Raj Dabre and
               Sadao Kurohashi},
  title     = {An Empirical Comparison of Simple Domain Adaptation Methods for Neural
               Machine Translation},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1701.03214},
  year      = {2017}
 }
@@ -14393,7 +14393,7 @@ author    = {Zhuang Liu and
  year      = {2010}
 }
-@article{vilar2012jane,
+@inproceedings{vilar2012jane,
  title={Jane: an advanced freely available hierarchical machine translation toolkit},
  author={Vilar, David and Stein, Daniel and Huck, Matthias and Ney, Hermann},
  publisher={Machine Translation},
@@ -14413,7 +14413,7 @@ author    = {Zhuang Liu and
  year      = {2013}
 }
-@article{al2016theano,
+@inproceedings{al2016theano,
  author    = {Rami Al-Rfou and
               Guillaume Alain and
               Amjad Almahairi and
@@ -14528,7 +14528,7 @@ author    = {Zhuang Liu and
               Ying Zhang},
  title     = {Theano: {A} Python framework for fast computation of mathematical
               expressions},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1605.02688},
  year      = {2016}
 }
@@ -14583,11 +14583,11 @@ author    = {Zhuang Liu and
  year      = {2007}
 }
-@article{och2003systematic,
+@inproceedings{och2003systematic,
  author    = {Franz Josef Och and
               Hermann Ney},
  title     = {A Systematic Comparison of Various Statistical Alignment Models},
-  journal   = {Computational Linguistics},
+  publisher   = {Computational Linguistics},
  volume    = {29},
  number    = {1},
  pages     = {19--51},
@@ -14661,7 +14661,7 @@ author    = {Zhuang Liu and
  year      = {2016}
 }
-@article{ZhangTHUMT,
+@inproceedings{ZhangTHUMT,
  author    = {Jiacheng Zhang and
               Yanzhuo Ding and
               Shiqi Shen and
@@ -14670,7 +14670,7 @@ author    = {Zhuang Liu and
               Huan-Bo Luan and
               Yang Liu},
  title     = {{THUMT:} An Open Source Toolkit for Neural Machine Translation},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1706.06415},
  year      = {2017}
 }
@@ -14694,7 +14694,7 @@ author    = {Zhuang Liu and
  year      = {2018}
 }
-@article{hieber2017sockeye,
+@inproceedings{hieber2017sockeye,
  author    = {Felix Hieber and
               Tobias Domhan and
               Michael Denkowski and
@@ -14703,7 +14703,7 @@ author    = {Zhuang Liu and
               Ann Clifton and
               Matt Post},
  title     = {Sockeye: {A} Toolkit for Neural Machine Translation},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1712.05690},
  year      = {2017}
 }
@@ -14719,7 +14719,7 @@ author    = {Zhuang Liu and
  year      = {2018}
 }
-@article{DBLP:journals/corr/abs-1805-10387,
+@inproceedings{DBLP:journals/corr/abs-1805-10387,
  author    = {Oleksii Kuchaiev and
               Boris Ginsburg and
               Igor Gitman and
@@ -14728,12 +14728,12 @@ author    = {Zhuang Liu and
               Paulius Micikevicius},
  title     = {OpenSeq2Seq: extensible toolkit for distributed and mixed precision
               training of sequence-to-sequence models},
-  journal   = {CoRR},
+  publisher   = {CoRR},
  volume    = {abs/1805.10387},
  year      = {2018}
 }
-@article{nmtpy2017,
+@inproceedings{nmtpy2017,
  author    = {Ozan Caglayan and
               Mercedes Garc{\'{\i}}a-Mart{\'{\i}}nez and
               Adrien Bardet and
@@ -14742,7 +14742,7 @@ author    = {Zhuang Liu and
               Lo{\"{\i}}c Barrault},
  title     = {{NMTPY:} {A} Flexible Toolkit for Advanced Neural Machine Translation
               Systems},
-  journal   = {The Prague Bulletin of Mathematical Linguistics},
+  publisher   = {The Prague Bulletin of Mathematical Linguistics},
  volume    = {109},
  pages     = {15--28},
  year      = {2017}