Skip to content

M
mtbookv2
Commit 3f391056 by 孟霞
Options

ref of chapter 9

parent 7082772e
正在显示 包含 405 行增加 和 0 行删除
bibliography.bib
......@@ -3508,6 +3508,411 @@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% chapter 9------------------------------------------------------
@article{brown1992class,
title={Class-based n-gram models of natural language},
author={Brown and
Peter F and
Desouza and
Peter V and
Mercer amd
Robert L
and Pietra and
Vincent J Della
and Lai and
Jenifer C},
journal={Computational linguistics},
volume={18},
number={4},
pages={467--479},
year={1992},
publisher={MIT Press}
}
@inproceedings{mikolov2012context,
title={Context dependent recurrent neural network language model},
author={Mikolov and
Tomas and
Zweig and
Geoffrey},
booktitle={2012 IEEE Spoken Language Technology Workshop (SLT)},
pages={234--239},
year={2012},
organization={IEEE}
}
@article{zaremba2014recurrent,
title={Recurrent Neural Network Regularization},
author={Zaremba and
Wojciech and
Sutskever and
Ilya and
Vinyals and
Oriol},
journal={arXiv: Neural and Evolutionary Computing},
year={2014}
}
@article{zilly2016recurrent,
title={Recurrent Highway Networks},
author={Zilly and
Julian and
Srivastava and
Rupesh Kumar and
Koutnik and
Jan and
Schmidhuber and
Jurgen},
journal={arXiv: Learning},
year={2016}
}
@article{merity2017regularizing,
title={Regularizing and optimizing LSTM language models},
author={Merity and
tephen and
Keskar and
Nitish Shirish and
Socher and
Richard},
journal={arXiv: Computation and Language},
year={2017}
}
@article{radford2019language,
title ={Language models are unsupervised multitask learners},
author ={Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
journal ={OpenAI Blog},
volume ={1},
number ={8},
pages ={9},
year ={2019}
}
@article{baydin2017automatic,
title ={Automatic differentiation in machine learning: a survey},
author ={Baydin, At{\i}l{\i}m G{\"u}nes and Pearlmutter, Barak A and Radul, Alexey Andreyevich and Siskind, Jeffrey Mark},
journal ={The Journal of Machine Learning Research},
volume ={18},
number ={1},
pages ={5595--5637},
year ={2017},
publisher ={JMLR. org}
}
@article{qian1999momentum,
author = {Ning Qian},
title = {On the momentum term in gradient descent learning algorithms},
journal = {Neural Networks},
volume = {12},
number = {1},
pages = {145--151},
year = {1999},
//url = {https://doi.org/10.1016/S0893-6080(98)00116-6},
//doi = {10.1016/S0893-6080(98)00116-6},
//timestamp = {Wed, 14 Nov 2018 10:30:22 +0100},
//biburl = {https://dblp.org/rec/journals/nn/Qian99.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{duchi2011adaptive,
author = {John C. Duchi and
Elad Hazan and
Yoram Singer},
title = {Adaptive Subgradient Methods for Online Learning and Stochastic Optimization},
journal = {Journal of Machine Learning Research},
volume = {12},
pages = {2121--2159},
year = {2011},
//url = {http://dl.acm.org/citation.cfm?id=2021068},
//timestamp = {Wed, 10 Jul 2019 15:28:02 +0200},
//biburl = {https://dblp.org/rec/journals/jmlr/DuchiHS11.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{tieleman2012rmsprop,
title ={Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude},
author ={Tieleman, Tijmen and Hinton, Geoffrey},
journal ={COURSERA: Neural networks for machine learning},
volume ={4},
number ={2},
pages ={26--31},
year ={2012}
}
@inproceedings{kingma2014adam,
author = {Diederik P. Kingma and
Jimmy Ba},
//editor = {Yoshua Bengio and
Yann LeCun},
title = {Adam: {A} Method for Stochastic Optimization},
booktitle = {3rd International Conference on Learning Representations, {ICLR} 2015,
San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings},
year = {2015},
//url = {http://arxiv.org/abs/1412.6980},
//timestamp = {Thu, 25 Jul 2019 14:25:37 +0200},
//biburl = {https://dblp.org/rec/journals/corr/KingmaB14.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{ioffe2015batch,
author = {Sergey Ioffe and
Christian Szegedy},
//editor = {Francis R. Bach and
David M. Blei},
title = {Batch Normalization: Accelerating Deep Network Training by Reducing
Internal Covariate Shift},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {448--456},
publisher = {JMLR.org},
year = {2015},
//url = {http://proceedings.mlr.press/v37/ioffe15.html},
//timestamp = {Wed, 29 May 2019 08:41:45 +0200},
//biburl = {https://dblp.org/rec/conf/icml/IoffeS15.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Ba2016LayerN,
author = {Lei Jimmy Ba and
Jamie Ryan Kiros and
Geoffrey E. Hinton},
title = {Layer Normalization},
journal = {CoRR},
volume = {abs/1607.06450},
year = {2016},
//url = {http://arxiv.org/abs/1607.06450},
//archivePrefix = {arXiv},
//eprint = {1607.06450},
//timestamp = {Tue, 23 Jul 2019 17:33:23 +0200},
//biburl = {https://dblp.org/rec/journals/corr/BaKH16.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/corr/HeZRS15,
author = {Kaiming He and
Xiangyu Zhang and
Shaoqing Ren and
Jian Sun},
title = {Deep Residual Learning for Image Recognition},
booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2016, Las Vegas, NV, USA, June 27-30, 2016},
pages = {770--778},
publisher = {{IEEE} Computer Society},
year = {2016},
//url = {https://doi.org/10.1109/CVPR.2016.90},
//doi = {10.1109/CVPR.2016.90},
//timestamp = {Wed, 16 Oct 2019 14:14:50 +0200},
//biburl = {https://dblp.org/rec/conf/cvpr/HeZRS16.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{mikolov2013distributed,
author = {Tomas Mikolov and
Ilya Sutskever and
Kai Chen and
Gregory S. Corrado and
Jeffrey Dean},
//editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Distributed Representations of Words and Phrases and their Compositionality},
booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual
Conference on Neural Information Processing Systems 2013. Proceedings
of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},
pages = {3111--3119},
year = {2013},
//url = {http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality},
//timestamp = {Fri, 06 Mar 2020 17:00:12 +0100},
//biburl = {https://dblp.org/rec/conf/nips/MikolovSCCD13.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{guidotti2018survey,
author = {Riccardo Guidotti and
Anna Monreale and
Salvatore Ruggieri and
Franco Turini and
Fosca Giannotti and
Dino Pedreschi},
title = {A Survey of Methods for Explaining Black Box Models},
journal = {ACM Computing Surveys},
volume = {51},
number = {5},
pages = {93:1--93:42},
year = {2019},
//url = {https://doi.org/10.1145/3236009},
//doi = {10.1145/3236009},
//timestamp = {Thu, 09 May 2019 16:06:21 +0200},
//biburl = {https://dblp.org/rec/journals/csur/GuidottiMRTGP19.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{koh2017understanding,
author = {Pang Wei Koh and
Percy Liang},
//editor = {Doina Precup and
Yee Whye Teh},
title = {Understanding Black-box Predictions via Influence Functions},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {1885--1894},
publisher = {{PMLR}},
year = {2017},
//url = {http://proceedings.mlr.press/v70/koh17a.html},
//timestamp = {Wed, 29 May 2019 08:41:45 +0200},
//biburl = {https://dblp.org/rec/conf/icml/KohL17.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{arthur2016incorporating,
author = {Philip Arthur and
Graham Neubig and
Satoshi Nakamura},
//editor = {Jian Su and
Xavier Carreras and
Kevin Duh},
title = {Incorporating Discrete Translation Lexicons into Neural Machine Translation},
booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2016, Austin, Texas, USA, November 1-4,
2016},
pages = {1557--1567},
publisher = {The Association for Computational Linguistics},
year = {2016},
//url = {https://doi.org/10.18653/v1/d16-1162},
//doi = {10.18653/v1/d16-1162},
//timestamp = {Tue, 28 Jan 2020 10:28:31 +0100},
//biburl = {https://dblp.org/rec/conf/emnlp/ArthurNN16.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{zollmann2006syntax,
author = {Andreas Zollmann and
Ashish Venugopal},
//editor = {Philipp Koehn and
Christof Monz},
title = {Syntax Augmented Machine Translation via Chart Parsing},
booktitle = {Proceedings on the Workshop on Statistical Machine Translation, WMT@HLT-NAACL
2006, New York City, NY, USA, June 8-9, 2006},
pages = {138--141},
publisher = {Association for Computational Linguistics},
year = {2006},
//url = {https://www.aclweb.org/anthology/W06-3119/},
//timestamp = {Fri, 13 Sep 2019 13:08:46 +0200},
//biburl = {https://dblp.org/rec/conf/wmt/ZollmannV06.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@INPROCEEDINGS{charniak2003syntax,
author = {Eugene Charniak and Kevin Knight and Kenji Yamada},
title = {Syntax-based Language Models for Statistical Machine Translation},
booktitle = {In MT Summit IX. Intl. Assoc. for Machine Translation},
year = {2003}
}
@inproceedings{stahlberg2016syntactically,
author = {Felix Stahlberg and
Eva Hasler and
Aurelien Waite and
Bill Byrne},
title = {Syntactically Guided Neural Machine Translation},
booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational
Linguistics, {ACL} 2016, August 7-12, 2016, Berlin, Germany, Volume
2: Short Papers},
publisher = {The Association for Computer Linguistics},
year = {2016},
//url = {https://doi.org/10.18653/v1/p16-2049},
//doi = {10.18653/v1/p16-2049},
//timestamp = {Tue, 28 Jan 2020 10:27:31 +0100},
//biburl = {https://dblp.org/rec/conf/acl/StahlbergHWB16.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{plank2013embedding,
author = {Barbara Plank and
Alessandro Moschitti},
title = {Embedding Semantic Similarity in Tree Kernels for Domain Adaptation
of Relation Extraction},
booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational
Linguistics, {ACL} 2013, 4-9 August 2013, Sofia, Bulgaria, Volume
1: Long Papers},
pages = {1498--1507},
publisher = {The Association for Computer Linguistics},
year = {2013},
//url = {https://www.aclweb.org/anthology/P13-1147/},
//timestamp = {Mon, 19 Aug 2019 18:10:05 +0200},
//biburl = {https://dblp.org/rec/conf/acl/PlankM13.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{perozzi2014deepwalk,
author = {Bryan Perozzi and
Rami Al{-}Rfou and
Steven Skiena},
//editor = {Sofus A. Macskassy and
Claudia Perlich and
Jure Leskovec and
Wei Wang and
Rayid Ghani},
title = {DeepWalk: online learning of social representations},
booktitle = {The 20th {ACM} {SIGKDD} International Conference on Knowledge Discovery
and Data Mining, {KDD} '14, New York, NY, {USA} - August 24 - 27,
2014},
pages = {701--710},
publisher = {{ACM}},
year = {2014},
//url = {https://doi.org/10.1145/2623330.2623732},
//doi = {10.1145/2623330.2623732},
//timestamp = {Sun, 02 Jun 2019 21:11:52 +0200},
//biburl = {https://dblp.org/rec/conf/kdd/PerozziAS14.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{collobert2011natural,
author = {Ronan Collobert and
Jason Weston and
L{\'{e}}on Bottou and
Michael Karlen and
Koray Kavukcuoglu and
Pavel P. Kuksa},
title = {Natural Language Processing (Almost) from Scratch},
journal = {Journal of Machine Learning Research},
volume = {12},
pages = {2493--2537},
year = {2011},
//url = {http://dl.acm.org/citation.cfm?id=2078186},
//timestamp = {Wed, 10 Jul 2019 15:28:44 +0200},
//biburl = {https://dblp.org/rec/journals/jmlr/CollobertWBKKK11.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{mccann2017learned,
author = {Bryan McCann and
James Bradbury and
Caiming Xiong and
Richard Socher},
//editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Learned in Translation: Contextualized Word Vectors},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, 4-9 December 2017,
Long Beach, CA, {USA}},
pages = {6294--6305},
year = {2017},
//url = {http://papers.nips.cc/paper/7209-learned-in-translation-contextualized-word-vectors},
//timestamp = {Fri, 06 Mar 2020 16:57:53 +0100},
//biburl = {https://dblp.org/rec/conf/nips/McCannBXS17.bib},
//bibsource = {dblp computer science bibliography, https://dblp.org}
}
%%%%% chapter 9------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论