This repository contains landmark research papers and blogs in Natural Language Processing that came out in this century.
Reading a paper is not the same as reading a blogpost or a novel. Here are a few handy resources to help you get started.
- How to read an academic article
- Advice on reading academic papers
- How to read and understand a scientific paper
- Should I Read Papers?
- The Refreshingly Rewarding Realm of Research Papers
- Sequence to Sequence Learning with Neural Network - LSTMN based approach for sequence problems.
- Learning Phase Representations using RNN Encoder-Decoder for statistical Machine Translation
- Attention Model(Neural Machine Translation By Jointly learning to Align and Translate) - Attention model architecture modified version for encoder decoder models (Don't confuse with Attention is all you need paper i.e, for transformers concept)
- Understanding Back-Translation at Scale
- MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
- Scaling Neural Machine Translation
- The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
- Convolutional Sequence to Sequence Learning- Modified Attention model with convolutional layer
- Scalable Hierarchical Distributed Language Model
- Bag of Tricks for Efficient Text Classification - fastText(by Facebook AI Research) trained on billion of words for text classification.
- Language Models are Unsupervised Multitask Learners
- Hierarchical Probabilistic Neural Network Language Model - Speed up training and recogintion(by 200) - Yoshua Bengio
- Distributed Representations of Sentences and Documents - Sentence/Document to vectors by Tomas Mikolov by Google
- Distributed Representations of Words and Phrases and their Compositionality- WOrd2Vec representation by Tomas Mikolov(Google)
- Efficient Estimation of Word Representations in Vector Space - High quality vector representation from huge data sets by Tomas Mikolov(Google)
- Deep contextualized word representations- based on deep birectional Language Model by Allen Institute for Artificial Intelligence
- Enriching Word Vectors with Subword Information - Handles morphology and generates vectors for words not present in training dataset by Facebook AI Research
- Misspelling Oblivious Word Embeddings
- Neural Image Caption Generation with Visual Attention
- Deep Visual-Semantic Alignments for Generating Image Descriptions
- Attention Is All You Need
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding - Multimodal Recurrent Neural Network architecture for image description by Andrej Kaparthy
and Le-Fei-fei
- The Illustrated Transformer - Transformers Research paper core details explained by Jalammar
- The Illustrated BERT - BERT is explained by Jalammar
- A Visual Guide to Using BERT for the First Time 💥 - Very beautifully explained BERT architecture with the help of visuals.