001-report.bib

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% You will put your bibliography in this file, use "online" for web
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@online{web001,
    title = {Word2vec},
    url = {https://www.tensorflow.org/tutorials/word2vec/},
}
@online{web004,
    title = {fastText},
    url = {https://github.com/facebookresearch/fastText} }
@online{web005,
    title = {LSTM-analyticsvidhya},
    url = {https://www.analyticsvidhya.com/blog/2017/12/fundamentals-of-deep-learning-introduction-to-lstm} }
@online{web006,
    title = {Python Def.},
    url = {https://en.wikipedia.org/wiki/Python_(programming_language)},
}
@online{web007,
    title = {Advantages-and-Disadvantages-of-Python},
    url = {https://www.quora.com/What-are-advantages-and-disadvantages-of-Python},
}
@online{web008,
    title = {GPUs},
    url = {https://en.wikipedia.org/wiki/Graphics_processing_unit#Hardware},
}
@online{web009,
    title = {nVIDIA},
    url = {https://en.wikipedia.org/wiki/Nvidia},
}
@online{web010,
    title = {HW acceleration},
    url = {https://en.wikipedia.org/wiki/Hardware_acceleration},
}
@online{web011,
    title = {NLP},
    url = {https://en.wikipedia.org/wiki/Natural_language_processing},
}
@online{web012,
    title = {NLM},
    url = {https://machinelearningmastery.com/statistical-language-modeling-and-neural-language-models},
}
@online{web013,
    title = {dynamic Rnn},
    url = {https://r2rt.com/recurrent-neural-networks-in-tensorflow-ii.html},
}
@online{web014,
    title = {Unrolling Rnn},
    url = {https://machinelearningmastery.com/rnn-unrolling},
}
@online{web015,
    title = {seq2seq learning with NNs},
    url = {https://arxiv.org/pdf/1409.3215.pdf},
}
@online{web016,
    title = {NMT with seq2seq},
    url = {https://github.com/stanfordnlp/cs224n-winter17-notes/blob/master/notes6.pdf},
}
@online{web017,
    title = {NMT-seq2seq},
    url = {https://github.com/tensorflow/nmt},
}
@online{web018,
    title = {encoder-decoder},
    url = {https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/21_Machine_Translation.ipynb},
}
@online{web019,
    title = {Attention in DNN},
    url = {http://www.wildml.com/2016/01/attention-and-memory-in-deep-learning-and-nlp},
}
@online{web020,
    title = {Areas Attention},
    url = {https://machinelearningmastery.com/attention-long-short-term-memory-recurrent-neural-networks},
}
@online{web021,
    title = {frameworks},
    url = {https://dzone.com/articles/8-best-deep-learning-frameworks} }

@online{web022,
    title = {Tensors},
    url = {https://www.tensorflow.org/programmers_guide/tensors} }

@online{web023,
    title = {Variables},
    url = {https://www.tensorflow.org/api_docs/python/tf/Variable} }

@online{web024,
    title = {Constants},
    url = {https://learningtensorflow.com/lesson4/} }

@online{web025,
    title = {TensorFlow},
    url = {https://www.tensorflow.org} }
@online{web026,
    title = {stanford.edu},
    url = {http://web.stanford.edu/class/cs20si/syllabus.html} }

@online{web027,
    title = {RMSPropOptimizer},
    url = {https://www.tensorflow.org/api_docs/python/tf/train/RMSPropOptimizer} }


@online{web028,
    title = {Backpropagation},
    url = {https://en.wikipedia.org/wiki/Backpropagation} }

@online{web029,
    title = {wsgi},
    url = {https://wsgi.readthedocs.io/en/latest/} }

@online{web030,
    title = {werkzeug},
    url = {https://www.palletsprojects.com/p/werkzeug/} }

@online{web031,
    title = {jinja},
    url = {https://www.palletsprojects.com/p/jinja/} }
@online{web032,
    title = {Wikipedia},
    url = {https://dumps.wikimedia.org/enwiki/latest/}
}
@online{web033,
    title = {Wikipediaextractor},
    url = {https://github.com/attardi/wikiextractor/}
}

@online{web034,
    title = {wikimovies},
    url = {https://research.fb.com/downloads/babi/}
}

@online{web035,
    title = {WebQuestions},
    url = {https://nlp.stanford.edu/software/sempre/}
}

@online{web036,
    title = {Trec},
    url = {https://trec.nist.gov/data/qa.html}
}


@online{web037,
    title = {featurization},
    url = {https://datascience.stackexchange.com/questions/586/what-are-the-main-types-of-nlp-annotators}
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@inproceedings{Gal:2016:TGA:3157096.3157211,
    author = {Gal, Yarin and Ghahramani, Zoubin},
    title = {A Theoretically Grounded Application of Dropout in Recurrent Neural Networks},
    booktitle = {Proceedings of the 30th International Conference on Neural Information Processing Systems},
    series = {NIPS'16},
    year = {2016},
    isbn = {978-1-5108-3881-9},
    location = {Barcelona, Spain},
    pages = {1027--1035},
    numpages = {9},
    url = {http://dl.acm.org/citation.cfm?id=3157096.3157211},
    acmid = {3157211},
    publisher = {Curran Associates Inc.},
    address = {USA},
}
@inproceedings{69e088c8129341ac89810907fe6b1bfe,
    title = "Empirical evaluation of gated recurrent neural networks on sequence modeling",
    author = "Junyoung Chung and Caglar Gulcehre and Kyunghyun Cho and Yoshua Bengio",
    year = "2014",
    language = "English (US)",
    booktitle = "NIPS 2014 Workshop on Deep Learning, December 2014",
}
@article{Hochreiter:1997:LSM:1246443.1246450,
    author = {Hochreiter, Sepp and Schmidhuber, J\" { u } rgen},
    title = {Long Short-Term Memory},
    journal = {Neural Comput.},
    issue_date = {November 15, 1997},
    volume = {9},
    number = {8},
    month = nov,
    year = {1997},
    issn = {0899-7667},
    pages = {1735--1780},
    numpages = {46},
    url = {http://dx.doi.org/10.1162/neco.1997.9.8.1735},
    doi = {10.1162/neco.1997.9.8.1735},
    acmid = {1246450},
    publisher = {MIT Press},
    address = {Cambridge, MA, USA},
}
@ARTICLE{Chung-et-al-TR2014,
    author = {Chung, Junyoung and G { \" { u } } l { \c c } ehre, { \c C } ağlar and Cho, Kyunghyun and Bengio, Yoshua},
    title = {Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling},
    journal = {arXiv e-prints},
    volume = {abs/1412.3555},
    year = {2014},
    note = {Presented at the Deep Learning workshop at NIPS2014},
    url = {https://arxiv.org/abs/1412.3555}
}
@book{bazerman1988shaping,
    title = {Shaping written knowledge: The genre and activity of the experimental article in science},
    author = {Bazerman, Charles and others},
    volume = {356},
    year = {1988},
    publisher = {University of Wisconsin Press Madison}
}
@article{DBLP:journals/corr/abs-1301-3781,
author = {Tomas Mikolov and
 Kai Chen and
 Greg Corrado and
 Jeffrey Dean},
title = {Efficient Estimation of Word Representations in Vector Space},
journal = {CoRR},
volume = {abs/1301.3781},
year = {2013},
url = {http://arxiv.org/abs/1301.3781},
archivePrefix = {arXiv},
eprint = {1301.3781},
timestamp = {Wed, 07 Jun 2017 14:42:25 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/abs-1301-3781},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MikolovSCCD13,
author = {Tomas Mikolov and
 Ilya Sutskever and
 Kai Chen and
 Greg Corrado and
 Jeffrey Dean},
title = {Distributed Representations of Words and Phrases and their Compositionality},
journal = {CoRR},
volume = {abs/1310.4546},
year = {2013},
url = {http://arxiv.org/abs/1310.4546},
archivePrefix = {arXiv},
eprint = {1310.4546},
timestamp = {Wed, 07 Jun 2017 14:40:03 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/MikolovSCCD13},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{pennington2014glove,
author = {Jeffrey Pennington and Richard Socher and Christopher D. Manning},
booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
title = {GloVe: Global Vectors for Word Representation},
year = {2014},
pages = {1532--1543},
url = {http://www.aclweb.org/anthology/D14-1162},
}
@inproceedings{DBLP:conf/acl/YinS16,
author = {Wenpeng Yin and
 Hinrich Sch { \" { u }} tze},
title = {Learning Word Meta-Embeddings},
booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational
 Linguistics, { ACL } 2016, August 7-12, 2016, Berlin, Germany, Volume
 1: Long Papers},
year = {2016},
url = {http://aclweb.org/anthology/P/P16/P16-1128.pdf},
timestamp = {Wed, 01 Feb 2017 10:48:29 +0100},
biburl = {https://dblp.org/rec/bib/conf/acl/YinS16},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Dyer14,
author = {Chris Dyer},
title = {Notes on Noise Contrastive Estimation and Negative Sampling},
journal = {CoRR},
volume = {abs/1410.8251},
year = {2014},
url = {http://arxiv.org/abs/1410.8251},
archivePrefix = {arXiv},
eprint = {1410.8251},
timestamp = {Wed, 07 Jun 2017 14:42:59 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/Dyer14},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{levy2014dependencybased,
added-at = {2014-12-13T13:15:51.000+0100},
address = {Baltimore, Maryland},
author = {Levy, Omer and Goldberg, Yoav},
biburl = {https://www.bibsonomy.org/bibtex/2c08ef42c3320976b65a9833180815f0e/gchrupala},
booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
interhash = {ec04086ee882f28c71d67260e100f2e5},
intrahash = {c08ef42c3320976b65a9833180815f0e},
keywords = {imported},
month = {June},
pages = {302--308},
publisher = {Association for Computational Linguistics},
timestamp = {2014-12-13T13:16:07.000+0100},
title = {Dependency-Based Word Embeddings},
url = {http://www.aclweb.org/anthology/P14-2050},
year = 2014
}

@misc{tensorflow2015-whitepaper,
title ={ { TensorFlow } : Large-Scale Machine Learning on Heterogeneous Systems},
url ={https://www.tensorflow.org/},
note ={Software available from tensorflow.org},
author ={
Mart\' { \i } n~Abadi and
 Ashish~Agarwal and
 Paul~Barham and
    Eugene~Brevdo and
 Zhifeng~Chen and
 Craig~Citro and
 Greg~S.~Corrado and
 Andy~Davis and
    Jeffrey~Dean and
 Matthieu~Devin and
 Sanjay~Ghemawat and
 Ian~Goodfellow and
 Andrew~Harp and
    Geoffrey~Irving and
 Michael~Isard and
 Yangqing Jia and
 Rafal~Jozefowicz and
 Lukasz~Kaiser and
 Manjunath~Kudlur and
 Josh~Levenberg and
 Dandelion~Man\' { e } and
    Rajat~Monga and
 Sherry~Moore and
 Derek~Murray and
 Chris~Olah and
 Mike~Schuster and
    Jonathon~Shlens and
 Benoit~Steiner and
 Ilya~Sutskever and
 Kunal~Talwar and
 Paul~Tucker and
    Vincent~Vanhoucke and
 Vijay~Vasudevan and
 Fernanda~Vi\' { e } gas and
    Oriol~Vinyals and
 Pete~Warden and
 Martin~Wattenberg and
 Martin~Wicke and
 Yuan~Yu and
    Xiaoqiang~Zheng},
year ={2015},
}
@incollection{NIPS2009_3793,
title = {Efficient Learning using Forward-Backward Splitting},
author = {Singer, Yoram and Duchi, John C},
booktitle = {Advances in Neural Information Processing Systems 22},
editor = {Y. Bengio and D. Schuurmans and J. D. Lafferty and C. K. I. Williams and A. Culotta},
pages = {495--503},
year = {2009},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/3793-efficient-learning-using-forward-backward-splitting.pdf}
}

@inproceedings{41159,
title = {Ad Click Prediction: a View from the Trenches},
author = {H. Brendan McMahan and Gary Holt and D. Sculley and Michael Young and Dietmar Ebner and Julian Grady and Lan Nie and Todd Phillips and Eugene Davydov and Daniel Golovin and Sharat Chikkerur and Dan Liu and Martin Wattenberg and Arnar Mar Hrafnkelsson and Tom Boulos and Jeremy Kubica},
year = {2013},
booktitle = {Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)}}
@article{Duchi:2011:ASM:1953048.2021068,
author = {Duchi, John and Hazan, Elad and Singer, Yoram},
title = {Adaptive Subgradient Methods for Online Learning and Stochastic Optimization},
journal = {J. Mach. Learn. Res.},
issue_date = {2/1/2011},
volume = {12},
month = jul,
year = {2011},
issn = {1532-4435},
pages = {2121--2159},
numpages = {39},
url = {http://dl.acm.org/citation.cfm?id=1953048.2021068},
acmid = {2021068},
publisher = {JMLR.org},
}

@article{DBLP:journals/corr/abs-1212-5701,
author = {Matthew D. Zeiler},
title = {{ ADADELTA: } An Adaptive Learning Rate Method},
journal = {CoRR},
volume = {abs/1212.5701},
year = {2012},
url = {http://arxiv.org/abs/1212.5701},
archivePrefix = {arXiv},
eprint = {1212.5701},
timestamp = {Wed, 07 Jun 2017 14:43:02 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/abs-1212-5701},
bibsource = {dblp computer science bibliography, https://dblp.org}}
@inproceedings{deeplearning,
title = {Pro Deep Learning with TensorFlow},
author = {Santanu Pattanayak},
year = {2017},
booktitle = {A Mathematical Approach to Advanced Artificial Intelligence in Python}}
@article{DBLP:journals/corr/KingmaB14,
author = {Diederik P. Kingma and
 Jimmy Ba},
title = {Adam: { A } Method for Stochastic Optimization},
journal = {CoRR},
volume = {abs/1412.6980},
year = {2014},
url = {http://arxiv.org/abs/1412.6980},
archivePrefix = {arXiv},
eprint = {1412.6980},
timestamp = {Wed, 07 Jun 2017 14:40:52 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/KingmaB14},
bibsource = {dblp computer science bibliography, https://dblp.org}
}


@article{DBLP:journals/corr/GravesWD14,
author = {Alex Graves and
 Greg Wayne and
 Ivo Danihelka},
title = {Neural Turing Machines},
journal = {CoRR},
volume = {abs/1410.5401},
year = {2014},
url = {http://arxiv.org/abs/1410.5401},
archivePrefix = {arXiv},
eprint = {1410.5401},
timestamp = {Wed, 07 Jun 2017 14:42:19 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/GravesWD14},
bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/SutskeverVL14,
author = {Ilya Sutskever and
 Oriol Vinyals and
 Quoc V. Le},
title = {Sequence to Sequence Learning with Neural Networks},
journal = {CoRR},
volume = {abs/1409.3215},
year = {2014},
url = {http://arxiv.org/abs/1409.3215},
archivePrefix = {arXiv},
eprint = {1409.3215},
timestamp = {Wed, 07 Jun 2017 14:40:10 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/SutskeverVL14},
bibsource = {dblp computer science bibliography, https://dblp.org}
}


@article{DBLP:journals/corr/BahdanauCB14,
author = {Dzmitry Bahdanau and
 Kyunghyun Cho and
 Yoshua Bengio},
title = {Neural Machine Translation by Jointly Learning to Align and Translate},
journal = {CoRR},
volume = {abs/1409.0473},
year = {2014},
url = {http://arxiv.org/abs/1409.0473},
archivePrefix = {arXiv},
eprint = {1409.0473},
timestamp = {Wed, 07 Jun 2017 14:40:19 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/BahdanauCB14},
bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/LuongPM15,
author = {Minh { - } Thang Luong and
 Hieu Pham and
               Christopher D. Manning},
title = {Effective Approaches to Attention-based Neural Machine Translation},
journal = {CoRR},
volume = {abs/1508.04025},
year = {2015},
url = {http://arxiv.org/abs/1508.04025},
archivePrefix = {arXiv},
eprint = {1508.04025},
timestamp = {Wed, 07 Jun 2017 14:41:36 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/LuongPM15},
bibsource = {dblp computer science bibliography, https://dblp.org}
}

@InProceedings{P17-1171,
  author = 	"Chen, Danqi
		and Fisch, Adam
		and Weston, Jason
		and Bordes, Antoine",
  title = 	"Reading Wikipedia to Answer Open-Domain Questions",
  booktitle = 	"Proceedings of the 55th Annual Meeting of the Association for      Computational Linguistics (Volume 1: Long Papers)    ",
  year = 	"2017",
  publisher = 	"Association for Computational Linguistics",
  pages = 	"1870--1879",
  location = 	"Vancouver, Canada",
  doi = 	"10.18653/v1/P17-1171",
  url = 	"http://www.aclweb.org/anthology/P17-1171"
}

@article{DBLP:journals/corr/ChenBM16a,
  author    = {Danqi Chen and
               Jason Bolton and
               Christopher D. Manning},
  title     = {A Thorough Examination of the CNN/Daily Mail Reading Comprehension
               Task},
  journal   = {CoRR},
  volume    = {abs/1606.02858},
  year      = {2016},
  url       = {http://arxiv.org/abs/1606.02858},
  archivePrefix = {arXiv},
  eprint    = {1606.02858},
  timestamp = {Wed, 07 Jun 2017 14:41:57 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/ChenBM16a},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}
ط@InProceedings{manning-EtAl:2014:P14-5,
  author    = {Manning, Christopher D. and  Surdeanu, Mihai  and  Bauer, John  and  Finkel, Jenny  and  Bethard, Steven J. and  McClosky, David},
  title     = {The {Stanford} {CoreNLP} Natural Language Processing Toolkit},
  booktitle = {Association for Computational Linguistics (ACL) System Demonstrations},
  year      = {2014},
  pages     = {55--60},
  url       = {http://www.aclweb.org/anthology/P/P14/P14-5010}
}