Skip to content

Instantly share code, notes, and snippets.

@MokkeMeguru
Created March 13, 2019 22:06
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
Star You must be signed in to star a gist
Save MokkeMeguru/38ec6962859fbe79954fac0f680604bf to your computer and use it in GitHub Desktop.
My reference for dialogue system
@misc{1605.06069,
Author = {Iulian Vlad Serban and Alessandro Sordoni and Ryan Lowe and Laurent Charlin and Joelle Pineau and Aaron Courville and Yoshua Bengio},
Title = {A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues},
Year = {2016},
Eprint = {arXiv:1605.06069},
}
@misc{1507.02221,
Author = {Alessandro Sordoni and Yoshua Bengio and Hossein Vahabi and Christina Lioma and Jakob G. Simonsen and Jian-Yun Nie},
Title = {A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion},
Year = {2015},
Eprint = {arXiv:1507.02221},
}
@article{1812.01525,
Author = {Hang Chu and Daiqing Li and Sanja Fidler},
Title = {A Face-to-Face Neural Conversation Model},
Year = {2018},
Eprint = {arXiv:1812.01525},
Howpublished = {CVPR (2018) 7113-7121},
}
@misc{rinna_article,
Author = {Xianchao Wo and Kazushige Ito and Katsuya Iida and Kazuna Tsubomi and Momo Klyen},
Title = {りんな:女子高生人工知能},
Year = {2016},
Month = {3},
Organization = {Microsoft Japan Inc},
Howpublished = {言語処理学会 第22回年次大会 発表論文集}
}
@misc{Gunrock,
Author = {Chun-Yen Chen and Dian Yu and Weiming Wen and Yi Mang Yang and Jiaping Zhang and Mingyang Zhou and Kevin Jesse and Austin Chau and Antara Bhowmick and Shreenath Iyer and Giritheja Sreenivasulu and Runxiang Cheng and Ashwin Bhandare and Zhou Yu},
Title = {Gunrock: Building A Human-Like Social Bot By Leveraging Large Scale Real User Data},
Year = {2018}
}
@misc{1804.10202,
Author = {Hao Fang and Hao Cheng and Maarten Sap and Elizabeth Clark and Ari Holtzman and Yejin Choi and Noah A. Smith and Mari Ostendorf},
Title = {Sounding Board: A User-Centric and Content-Driven Social Chatbot},
Year = {2018},
Eprint = {arXiv:1804.10202},
}
@book{meidai,
author={逸子,藤村 and 美恵子,大曽 and ディヴィッド義和,大島},
year={2011},
booktitile={会話コーパスの構築によるコミュニケーション研究},
title={言語研究の技法:データの収集と分析},
editor={藤村逸子、滝沢直宏},
publisher={ひつじ書房}
}
@inproceedings{imagenet_cvpr09,
AUTHOR = {Deng, J. and Dong, W. and Socher, R. and Li, L.-J. and Li, K. and Fei-Fei, L.},
TITLE = {{ImageNet: A Large-Scale Hierarchical Image Database}},
BOOKTITLE = {CVPR09},
YEAR = {2009},
BIBSOURCE = {"http://www.image-net.org/papers/imagenet_cvpr09.bib"}
}
@inproceedings{Papineni:2002:BMA:1073083.1073135,
author = {Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing},
title = {BLEU: A Method for Automatic Evaluation of Machine Translation},
booktitle = {Proceedings of the 40th Annual Meeting on Association for Computational Linguistics},
series = {ACL '02},
year = {2002},
location = {Philadelphia, Pennsylvania},
pages = {311--318},
numpages = {8},
url = {https://doi.org/10.3115/1073083.1073135},
doi = {10.3115/1073083.1073135},
acmid = {1073135},
publisher = {Association for Computational Linguistics},
address = {Stroudsburg, PA, USA},
}
@article{40020632863,
author="東中, 竜一郎 and 船越, 孝太郎 and 小林, 優佳",
title="対話破綻検出チャレンジ",
journal="言語・音声理解と対話処理研究会",
ISSN="0918-5682",
publisher="人工知能学会",
year="2015",
month=oct,
volume="75",
number="",
pages="27-32",
URL="https://ci.nii.ac.jp/naid/40020632863/",
DOI="",
}
@article{vanDerMaaten2008,
added-at = {2015-06-19T12:07:15.000+0200},
author = {van der Maaten, Laurens and Hinton, Geoffrey},
biburl = {https://www.bibsonomy.org/bibtex/28b9aebb404ad4a4c6a436ea413550b30/lopusz_kdd},
interhash = {370ba8b9e1909b61880a6f47c93bcd49},
intrahash = {8b9aebb404ad4a4c6a436ea413550b30},
journal = {Journal of Machine Learning Research},
keywords = {dimensionality_reduction tSNE visualization},
pages = {2579--2605},
timestamp = {2015-08-19T15:19:11.000+0200},
title = {Visualizing Data using {t-SNE} },
url = {http://www.jmlr.org/papers/v9/vandermaaten08a.html},
volume = 9,
year = 2008
}
@ARTICLE{Kalman96asingularly,
author = {Dan Kalman},
title = {A singularly valuable decomposition: The SVD of a matrix},
journal = {College Math Journal},
year = {1996},
volume = {27},
pages = {2--23}
}
@incollection{NIPS2013_5021,
title = {Distributed Representations of Words and Phrases and their Compositionality},
author = {Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg S and Dean, Jeff},
booktitle = {Advances in Neural Information Processing Systems 26},
editor = {C. J. C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K. Q. Weinberger},
pages = {3111--3119},
year = {2013},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf}
}
@INPROCEEDINGS{Pennington14glove:global,
author = {Jeffrey Pennington and Richard Socher and Christopher D. Manning},
title = {Glove: Global vectors for word representation},
booktitle = {In EMNLP},
year = {2014}
}
@article{Bojanowski2017EnrichingWV,
title={Enriching Word Vectors with Subword Information},
author={Piotr Bojanowski and Edouard Grave and Armand Joulin and Tomas Mikolov},
journal={TACL},
year={2017},
volume={5},
pages={135-146}
}
@inproceedings{Mikolov2013DistributedRO,
title={Distributed Representations of Words and Phrases and their Compositionality},
author={Tomas Mikolov and Ilya Sutskever and Kai Chen and Gregory S. Corrado and Jeffrey Dean},
booktitle={NIPS},
year={2013}
}
@article{fukushima:neocognitronbc,
added-at = {2008-03-11T14:52:34.000+0100},
author = {Fukushima, Kunihiko},
biburl = {https://www.bibsonomy.org/bibtex/29ecd878c4827c46dab6b9622cfa00072/idsia},
citeulike-article-id = {2376719},
interhash = {303975e6400e477e91c91e7dc2c47544},
intrahash = {9ecd878c4827c46dab6b9622cfa00072},
journal = {Biological Cybernetics},
keywords = {nn},
pages = {193--202},
priority = {2},
timestamp = {2008-03-11T15:04:22.000+0100},
title = {{N}eocognitron: {A} Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position},
volume = 36,
year = 1980
}
@inproceedings{LeCun:1999:ORG:646469.691875,
author = {LeCun, Yann and Haffner, Patrick and Bottou, L{\'e}on and Bengio, Yoshua},
title = {Object Recognition with Gradient-Based Learning},
booktitle = {Shape, Contour and Grouping in Computer Vision},
year = {1999},
isbn = {3-540-66722-9},
pages = {319--},
url = {http://dl.acm.org/citation.cfm?id=646469.691875},
acmid = {691875},
publisher = {Springer-Verlag},
address = {London, UK, UK},
}
@article{Schuster:1997:BRN:2198065.2205129,
author = {Schuster, M. and Paliwal, K.K.},
title = {Bidirectional Recurrent Neural Networks},
journal = {Trans. Sig. Proc.},
issue_date = {November 1997},
volume = {45},
number = {11},
month = nov,
year = {1997},
issn = {1053-587X},
pages = {2673--2681},
numpages = {9},
url = {http://dx.doi.org/10.1109/78.650093},
doi = {10.1109/78.650093},
acmid = {2205129},
publisher = {IEEE Press},
address = {Piscataway, NJ, USA},
}
@book{Jain:1999:RNN:553011,
author = {Jain, L. C. and Medsker, L. R.},
title = {Recurrent Neural Networks: Design and Applications},
year = {1999},
isbn = {0849371813},
edition = {1st},
publisher = {CRC Press, Inc.},
address = {Boca Raton, FL, USA},
}
@inproceedings{Elbayad2018PervasiveA2,
title={Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction},
author={Maha Elbayad and Laurent Besacier and Jakob Verbeek},
booktitle={CoNLL},
year={2018}
}
@inproceedings{Sutskever2014SequenceTS,
title={Sequence to Sequence Learning with Neural Networks},
author={Ilya Sutskever and Oriol Vinyals and Quoc V. Le},
booktitle={NIPS},
year={2014}
}
@inproceedings{Luong2015EffectiveAT,
title={Effective Approaches to Attention-based Neural Machine Translation},
author={Thang Luong and Hieu Pham and Christopher D. Manning},
booktitle={EMNLP},
year={2015}
}
@inproceedings{Vaswani2017AttentionIA,
title={Attention Is All You Need},
author={Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin},
booktitle={NIPS},
year={2017}
}
@article{DBLP:journals/corr/KingmaW13,
author = {Diederik P. Kingma and
Max Welling},
title = {Auto-Encoding Variational Bayes},
journal = {CoRR},
volume = {abs/1312.6114},
year = {2013},
url = {http://arxiv.org/abs/1312.6114},
archivePrefix = {arXiv},
eprint = {1312.6114},
timestamp = {Mon, 13 Aug 2018 16:49:01 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/KingmaW13},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{gans,
title = {Generative Adversarial Nets},
author = {Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
booktitle = {Advances in Neural Information Processing Systems 27},
editor = {Z. Ghahramani and M. Welling and C. Cortes and N. D. Lawrence and K. Q. Weinberger},
pages = {2672--2680},
year = {2014},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf}
}
@InProceedings{tcgt,
title = {Toward Controlled Generation of Text},
author = {Zhiting Hu and Zichao Yang and Xiaodan Liang and Ruslan Salakhutdinov and Eric P. Xing},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {1587--1596},
year = {2017},
editor = {Doina Precup and Yee Whye Teh},
volume = {70},
series = {Proceedings of Machine Learning Research},
address = {International Convention Centre, Sydney, Australia},
month = Aug,
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/hu17e/hu17e.pdf},
url = {http://proceedings.mlr.press/v70/hu17e.html},
abstract = {Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible text sentences, whose attributes are controlled by learning disentangled latent representations with designated semantics. We propose a new neural generative model which combines variational auto-encoders (VAEs) and holistic attribute discriminators for effective imposition of semantic structures. The model can alternatively be seen as enhancing VAEs with the wake-sleep algorithm for leveraging fake samples as extra training data. With differentiable approximation to discrete text samples, explicit constraints on independent attribute controls, and efficient collaborative learning of generator and discriminators, our model learns interpretable representations from even only word annotations, and produces short sentences with desired attributes of sentiment and tenses. Quantitative experiments using trained classifiers as evaluators validate the accuracy of sentence and attribute generation.}
}
@InProceedings{s2bs,
title = {Sequence to Better Sequence: Continuous Revision of Combinatorial Structures},
author = {Jonas Mueller and David Gifford and Tommi Jaakkola},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {2536--2544},
year = {2017},
editor = {Doina Precup and Yee Whye Teh},
volume = {70},
series = {Proceedings of Machine Learning Research},
address = {International Convention Centre, Sydney, Australia},
month = Aug,
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/mueller17a/mueller17a.pdf},
url = {http://proceedings.mlr.press/v70/mueller17a.html},
abstract = {We present a model that, after learning on observations of (sequence, outcome) pairs, can be efficiently used to revise a new sequence in order to improve its associated outcome. Our framework requires neither example improvements, nor additional evaluation of outcomes for proposed revisions. To avoid combinatorial-search over sequence elements, we specify a generative model with continuous latent factors, which is learned via joint approximate inference using a recurrent variational autoencoder (VAE) and an outcome-predicting neural network module. Under this model, gradient methods can be used to efficiently optimize the continuous latent factors with respect to inferred outcomes. By appropriately constraining this optimization and using the VAE decoder to generate a revised sequence, we ensure the revision is fundamentally similar to the original sequence, is associated with better outcomes, and looks natural. These desiderata are proven to hold with high probability under our approach, which is empirically demonstrated for revising natural language sentences.}
}
@inproceedings{Shen2017StyleTF,
title={Style Transfer from Non-Parallel Text by Cross-Alignment},
author={Tianxiao Shen and Tao Lei and Regina Barzilay and Tommi S. Jaakkola},
booktitle={NIPS},
year={2017}
}
@inproceedings{dae,
author = {Vincent, Pascal and Larochelle, Hugo and Bengio, Yoshua and Manzagol, Pierre-Antoine},
title = {Extracting and Composing Robust Features with Denoising Autoencoders},
booktitle = {Proceedings of the 25th International Conference on Machine Learning},
series = {ICML '08},
year = {2008},
isbn = {978-1-60558-205-4},
location = {Helsinki, Finland},
pages = {1096--1103},
numpages = {8},
url = {http://doi.acm.org/10.1145/1390156.1390294},
doi = {10.1145/1390156.1390294},
acmid = {1390294},
publisher = {ACM},
address = {New York, NY, USA},
}
@article{Gu2016IncorporatingCM,
title={Incorporating Copying Mechanism in Sequence-to-Sequence Learning},
author={Jiatao Gu and Zhengdong Lu and Hang Li and Victor O. K. Li},
journal={CoRR},
year={2016},
volume={abs/1603.06393}
}
@article{warstadt,
title={Neural Network Acceptability Judgments},
author={Warstadt, Alex and Singh, Amanpreet and Bowman, Samuel R},
journal={arXiv preprint arXiv:1805.12471},
year={2018}
}
@article{Devlin2018BERTPO,
title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
author={Jacob Devlin and Ming-Wei Chang and Kenton Lee and Kristina Toutanova},
journal={CoRR},
year={2018},
volume={abs/1810.04805}
}
@article{Forney:1973ly,
added-at = {2010-01-28T11:42:45.000+0100},
author = {Forney, G. D.},
biburl = {https://www.bibsonomy.org/bibtex/27b2ae314c64d34ca0cf52425ea541f7d/bfields},
date-added = {2009-11-11 15:57:43 +0000},
date-modified = {2009-11-11 15:57:43 +0000},
description = {initial imports},
interhash = {97657e6f35027dc83725e5c01ef3f21a},
intrahash = {7b2ae314c64d34ca0cf52425ea541f7d},
journal = {Proc. of the IEEE},
keywords = {HMM Viterbi},
month = Mar,
pages = {268 - 278},
rating = {4},
read = {Yes},
timestamp = {2010-01-28T11:42:47.000+0100},
title = {The Viterbi algorithm},
volume = 61,
year = 1973
}
@inproceedings{chinchor98,
added-at = {2007-12-12T23:57:17.000+0100},
address = {Fairfax, VA},
author = {Chinchor, Nancy A.},
biburl = {https://www.bibsonomy.org/bibtex/2774fb97f2a81eb6557254ec6a0fba7f3/deynard},
booktitle = {Proceedings of the Seventh Message Understanding Conference (MUC-7)},
interhash = {a610982840fd68df3da74d6c1937f783},
intrahash = {774fb97f2a81eb6557254ec6a0fba7f3},
keywords = {annotation semantic},
month = Apr,
note = {version 3.5, {\footnotesize http://www.itl.nist.gov/iaui/894.02/related\_projects/muc/}},
pages = {21 pages},
timestamp = {2007-12-12T23:57:17.000+0100},
title = {{{Proceedings of the Seventh Message Understanding Conference (MUC-7)}} Named Entity Task Definition},
url = {http://acl.ldc.upenn.edu/muc7/ne_task.html},
year = 1998
}
@inproceedings{Peters2018DeepCW,
title={Deep contextualized word representations},
author={Matthew E. Peters and Mark Neumann and Mohit Iyyer and Matt Gardner and Christopher Clark and Kenton Lee and Luke S. Zettlemoyer},
booktitle={NAACL-HLT},
year={2018}
}
@incollection{NIPS2012_4824,
title = {ImageNet Classification with Deep Convolutional Neural Networks},
author = {Alex Krizhevsky and Sutskever, Ilya and Hinton, Geoffrey E},
booktitle = {Advances in Neural Information Processing Systems 25},
editor = {F. Pereira and C. J. C. Burges and L. Bottou and K. Q. Weinberger},
pages = {1097--1105},
year = {2012},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf}
}
@article{Sainath2015ConvolutionalLS,
title={Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks},
author={Tara N. Sainath and Oriol Vinyals and Andrew W. Senior and Hasim Sak},
journal={2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year={2015},
pages={4580-4584}
}
@article{Chung2014EmpiricalEO,
title={Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling},
author={Junyoung Chung and Çaglar G{\"u}lçehre and Kyunghyun Cho and Yoshua Bengio},
journal={CoRR},
year={2014},
volume={abs/1412.3555}
}
@article{Clevert2015FastAA,
title={Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)},
author={Djork-Arn{\'e} Clevert and Thomas Unterthiner and Sepp Hochreiter},
journal={CoRR},
year={2015},
volume={abs/1511.07289}
}
@inproceedings{Nair:2010:RLU:3104322.3104425,
author = {Nair, Vinod and Hinton, Geoffrey E.},
title = {Rectified Linear Units Improve Restricted Boltzmann Machines},
booktitle = {Proceedings of the 27th International Conference on International Conference on Machine Learning},
series = {ICML'10},
year = {2010},
isbn = {978-1-60558-907-7},
location = {Haifa, Israel},
pages = {807--814},
numpages = {8},
url = {http://dl.acm.org/citation.cfm?id=3104322.3104425},
acmid = {3104425},
publisher = {Omnipress},
address = {USA},
}
@book{Goodfellow2016c10,
title={Deep Learning},
author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
publisher={MIT Press},
note={\url{http://www.deeplearningbook.org}},
year={2016},
chapter={10}
}
@book{Goodfellow2016c8,
title={Deep Learning},
author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
publisher={MIT Press},
note={\url{http://www.deeplearningbook.org}},
year={2016},
chapter={8}
}
@inproceedings{Graves:2005:BLN:1986079.1986220,
author = {Graves, Alex and Fern\'{a}ndez, Santiago and Schmidhuber, J\"{u}rgen},
title = {Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition},
booktitle = {Proceedings of the 15th International Conference on Artificial Neural Networks: Formal Models and Their Applications - Volume Part II},
series = {ICANN'05},
year = {2005},
% isbn = {3-540-28755-8, 978-3-540-28755-1},
location = {Warsaw, Poland},
pages = {799--804},
numpages = {6},
url = {http://dl.acm.org/citation.cfm?id=1986079.1986220},
acmid = {1986220},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
}
@article{Bahdanau2014NeuralMT,
title={Neural Machine Translation by Jointly Learning to Align and Translate},
author={Dzmitry Bahdanau and Kyunghyun Cho and Yoshua Bengio},
journal={CoRR},
year={2014},
volume={abs/1409.0473}
}
@inproceedings{
lample2018unsupervised,
title={Unsupervised Machine Translation Using Monolingual Corpora Only},
author={Guillaume Lample and Alexis Conneau and Ludovic Denoyer and Marc'Aurelio Ranzato},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=rkYTTf-AZ},
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment