└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | # Deep models for Paraphrase and Summarization
 2 | 
 3 | REFERENCE:
 4 | 
 5 | Zhao et al., Adversarially Regularized Autoencoders for Generating Discrete Structures.https://arxiv.org/abs/1706.04223 Git Repo: https://github.com/jakezhaojb/ARAE (Pytorch)
 6 | 
 7 | Kim et al., ADVERSARIALLY REGULARIZED AUTOENCODERS https://arxiv.org/pdf/1706.04223.pdf
 8 | 
 9 | Gutpa et al, A Deep Generative Framework for Paraphrase Generation. https://arxiv.org/abs/1709.05074. Dataset: https://data.quora.com/First-Quora-Dataset-Release-Question-Pairs
10 | 
11 | Samuel et al, Generating Sentences from a Continuous Space. https://arxiv.org/abs/1511.06349# Git Repo:https://github.com/kefirski/pytorch_RVAE (Pytorch) Git Repo:https://github.com/Chung-I/Variational-Recurrent-Autoencoder-Tensorflow (TF)
12 | 
13 | Neural Paraphrase Generation with Stacked Residual LSTM Networks. https://arxiv.org/abs/1610.03098 Git: https://github.com/iamaaditya/neural-paraphrase-generation
14 | 
15 | Paraphrase Generation with Deep Reinforcement Learning. https://arxiv.org/abs/1711.00279
16 | 
17 | Learning to Paraphrase for Question Answering. https://arxiv.org/abs/1708.06022
18 | 
19 | Goodfellow et al, EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES. https://arxiv.org/abs/1412.6572. (Adversarial training for continous input)
20 | 
21 | ## VAE
22 | 
23 | Hierarchical/ Mixture VAE/
24 | 
25 | Semi VAE/ Conditional VAE git: https://github.com/wohlert/semi-supervised-pytorch
26 | 
27 | Deep Recurrent Generative Decoder for Abstractive Text Summarization. https://arxiv.org/abs/1708.00625 Git: https://github.com/toru34/li_emnlp_2017
28 | 
29 | VAE Tutorial https://arxiv.org/abs/1606.05908
30 | 
31 | John Paisley http://www.columbia.edu/~jwp2128/Teaching/E6720/BayesianModelsMachineLearning2016.pdf. LECTURE 6 Variational Inference
32 | Carl Doersch, Tutorial on Variational Autoencoders, https://arxiv.org/abs/1606.05908
33 | 
34 | ## Knowledge Graph
35 | 
36 | Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks. https://arxiv.org/abs/1704.08384
37 | 
38 | Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks. https://arxiv.org/abs/1607.01426
39 | 
40 | Compositional Vector Space Models for Knowledge Base Inference. https://www.aaai.org/ocs/index.php/SSS/SSS15/paper/viewFile/10254/10032
41 | 
42 | Knowledge Graphs: https://people.mpi-inf.mpg.de/~weikum/weikum-adc2015-forwebsite.pdf
43 | 
44 | ## Command Lines
45 | 
46 | data preprocessing python make_datafiles_tokd.py ../data/tokened/ ../data/processed
47 | 
48 | 


--------------------------------------------------------------------------------