Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/shashi456/deep-learning-research

Summaries of papers on Deep Learning, Natural Language Processing, Computer vision
https://github.com/shashi456/deep-learning-research

artificial-intelligence computer-vision deep-learning deep-neural-networks hacktoberfest language-modeling machine-learning natural-language-processing neural-networks nlp research text-summarization

Last synced: 22 days ago
JSON representation

Summaries of papers on Deep Learning, Natural Language Processing, Computer vision

Awesome Lists containing this project

README 

        
# Research



Just a list of papers i read everyday and notes to keep a track of them. I used to read a variety of papers pre 2023 and you can look at them in the [Pre-2023 section](#pre-2023).



# 2nd September 2023



 



## Pre 2023

# Papers

These will either be paper implementations or/and reviews of various papers and notes for conference sessions, I will read/watch over time. I currently research on Abstractive Summarization ( A task within NLP) 



## Adversarial Examples

- Explaining and Harnessing Adversarial Examples [[Paper](https://arxiv.org/pdf/1412.6572v3.pdf)] [[Review](https://github.com/Shashi456/Papers/blob/master/Review/Explaining%20and%20Harnesssing%20Adversarial%20Examples.md)]

- Intriguing Properties of Neural Networks [[Paper](https://arxiv.org/abs/1312.6199)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Intriguing%20Properties%20of%20Neural%20Networks.md)]

- Practical BlackBox attacks against machine learning [[Paper](https://arxiv.org/abs/1602.02697)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Practical%20Black%20Box%20Attack%20against%20Machine%20Learning.md)]

--The Limitations of deep learning in adversarial settings [[Paper](https://arxiv.org/abs/151



## Neural Style

- Neural Algorithm of Artistic Style [[Paper](https://arxiv.org/pdf/1508.06576.pdf)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/A%20Neural%20Algorithm%20of%20Artistic%20Style.md)][[Code](https://github.com/Shashi456/Neural-Style)][[Article](https://towardsdatascience.com/neural-style-transfer-series-part-2-91baad306b24)]



## Image Classification

- Very Deep Convolutional Networks for Large Scale Image Recognition [[Paper](https://arxiv.org/pdf/1409.1556.pdf)][[Review](./Review/VGG.md)]



## One Shot Learning

- Siamese Neural networks for One-Shot Image Recognition [[Paper](https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Siamese%20Neural%20Networks%20for%20One-shot%20Image%20Recogniton.md)]

- Learning to compare: Relation Network for Few shot Learning  [[Paper](http://www.robots.ox.ac.uk/~tvg/publications/2018/0431.pdf)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/LTC%20Relation%20Network%20for%20few%20shot%20learning.md)][[Code](https://github.com/Shashi456/Papers/blob/master/Implementations/Learning%20to%20Compare%20-%20One%20shot%20Leanring/One%20Shot%20Classification(2).ipynb)]



## Natural Language Processing

## Sequence to Sequence Learning



- Sequence to Sequence Learning with Neural Networks. [[Paper](https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Sequence%20to%20Sequence%20Learning%20with%20Neural%20Networks.md)]



## Attention Based Models

- Neural Machine Translation by jointly learning to align and translate [[Paper](https://arxiv.org/abs/1409.0473)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Neural%20Machine%20Translation%20by%20Jointly%20learning%20to%20align%20and%20translate.md)]



## Text Classification

- Universal Language Model Fine-tuning for Text Classification [[Paper](https://arxiv.org/abs/1801.06146)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Universal%20Language%20Model%20Fine-Tuning%20for%20Text%20Classification.md)]



## Machine Translation

- Incorporating BERT for Machine Translation. 

[[Paper](https://arxiv.org/abs/2002.06823v1)][[Review](./Review/BERTMT.md)]



## Abstractive Summarization

- A Neural Attention Model for Abstractive Sentence Summarization [[Paper](https://arxiv.org/pdf/1509.00685.pdf)][[Review](Review/NeuralattnAbs.md)]

- Abstractive Text Summarization Using Sequence to Sequence RNNs and Beyond [[Paper](https://www.aclweb.org/anthology/K16-1028.pdf)][[Review](Review/AbstractiveTextSummUsingRNNs.md)]

- Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting [[Paper](https://arxiv.org/abs/1805.11080)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Fast%20Abstractive%20Summarization%20with%20Reinforce-Selected%20Sentence%20Rewriting.md)]

- Improving Abstraction in Text Summarization [[Paper](https://arxiv.org/abs/1808.07913)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Improving%20Abstraction%20in%20Text%20Summarization.md)]

- Multi-Reward Reinforced Summarization with Saliency and Entailment [[Paper](https://arxiv.org/abs/1804.06451)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Multi%20Reward%20Reinforced%20Summarization.md)]

- Bottom-Up Abstractive Summarization [[Paper](https://arxiv.org/abs/1808.10792)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/Bottom%20Up%20Abstractive%20Summarization.md)]

- Topic Augmented Generator for Abstractive Summarization [[Paper](https://arxiv.org/abs/1908.07026)][[Review](./Review/TopicAugmentedGenAbsSumm)]

- Earlier Isn’t Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization [[Paper](https://arxiv.org/abs/1908.11723)][[Review](./Review/SummBiases.md)]

- Neural Text Summarization: A Critical Evaluation [[Paper](https://www.aclweb.org/anthology/D19-1051.pdf)][[Review](./Review/NeuralTextSumm.md)]

- What have we achieved on Text Summarization [[Paper](https://arxiv.org/pdf/2010.04529.pdf)][[Review](./Review/WHWAIS.md)]

- Re-evaluating evaluaton in Text Summarization [[Paper](https://arxiv.org/pdf/2010.07100.pdf)][[Review](./Review/REITS.md)]

- Asking and answering questions to evaluate the factual consistency of summaries [[Paper](https://arxiv.org/pdf/2004.04228.pdf)][[Review](./Review/factconssumm.md)]

- On Faithfulness and Factuality in Abstractive Summarization [[Paper](https://arxiv.org/pdf/2005.00661.pdf)][[Review](./Review/OFFAS.md)]

- FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization [[Paper](https://arxiv.org/pdf/2005.03754.pdf)][[Review](./Review/FEQA.md)]

- Analyzing sentence fusion in Abstractive Summarization [[Paper](https://www.aclweb.org/anthology/D19-5413.pdf)][[Review](./Review/ASFAS.md)]

- On the Abstractiveness of Neural Document Summarization [[Paper](https://www.aclweb.org/anthology/D18-1089.pdf)][[Review](./Review/OANDS.md)]

- Evaluating the Factual Consistency of Abstractive Text Summarization. [[Paper](https://arxiv.org/pdf/1910.12840.pdf)][[Review](./Review/EFCATS.md)]

- Summ-Eval: Re-evaluating Summarization Evaluation [[Paper](https://arxiv.org/pdf/2007.12626.pdf)][[Review](./Review/summeval.md)]



### Topic-Based & Query-Based Summarization

- A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization [[Paper](https://arxiv.org/abs/1805.03616)][[Review](./Review/RConvS2Ssummarization.md)]

- Query-Based Abstractive Summarization Using Neural Networks [[Paper](https://arxiv.org/abs/1712.06100)][[Review](./Review/QueryBasedSummNN.md)]

- Transforming Wikipedia into Augmented Data for Query Focused Summarization [[Paper](https://arxiv.org/abs/1911.03324)][[Review](./Review/AugmentWikiforQueryBasedSumm.md)]

- Extreme Summarization with Topic Aware Convolutional Neural Networks [[Paper][[v2](https://arxiv.org/abs/1907.08722)][[v1](https://arxiv.org/pdf/1808.08745.pdf)]][[Review](./Review/XSUM.md)]



## Language Modeling

- CTRL: A Conditional Transformer Language Model for Controllable Generation [[Paper](https://arxiv.org/abs/1909.05858)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/CTRL.md)]



## Training

- Von Mises-Fisher Loss for training Seq2Seq Models with Continous Outputs [[Paper](https://arxiv.org/pdf/1812.04616.pdf)][[Review](https://github.com/Shashi456/Papers/blob/master/Review/VonMisesLoss.md)]

- Neural Text Degeneration with Unlikelihood Training [[Paper](https://arxiv.org/abs/1908.04319)][[Review](./Review/unlikelihooddegen.md)]

- The curious case of neural text degeneration [[Paper](https://arxiv.org/abs/1904.09751)] [[Review](./Review/ccdegen.md)]

- Parameter Selection: Why We Should Pay More Attention to It [[Paper](https://arxiv.org/abs/2107.05393)] [[Review](./Review/parasel.md)]



## Question Answering

- Generalizing Question Answering System with Pre-trained Language Model Fine-tuning [[Paper](https://www.aclweb.org/anthology/D19-5827/)][[Review](./Review/GeneralizingQAXLNET.md)]

- MULTI QA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension [[Paper](https://arxiv.org/abs/1905.13453)][[Review](./Review/MultiQA.md)]



## Word Representations and Embeddings 

- Deep Contextualized word representations - ELMO [[Paper](https://arxiv.org/abs/1802.05365)][[Review](./Review/ELMO.md)]

- Information-Theoretic Probing with Minimum Description Length [[Paper](https://arxiv.org/abs/2003.12298)][[Review](https://github.com/Shashi456/Deep-Learning-Papers/blob/master/Review/Information-Theretic%20Probing%20with%20Minimum%20Description%20Length.md)]

- SimCSE: Simple constrastive learning for sentence embeddings [[Paper](https://arxiv.org/pdf/2104.08821.pdf)] [[Review](./Review/SimCSE.md)]