Deep Learning for NLP: An Overview of Recent Trends

About this project

The main motivations for this project are as follows:

1. Maintain an up-to-date learning resource that integrates important information related to NLP research, such as:

• state of the art results

• emerging concepts and applications

• new benchmark datasets

• code/dataset releases

• etc.

2. Create a friendly and open resource to help guide researchers and anyone interested to learn about modern techniques applied to NLPA collaborative project where expert researchers can suggest changes (e.g., incorporate SOTA results) based on their recent findings and experimental results

Table of Contents

IntroductionDistributed Representation

Word Embeddings

Word2vec

Character Embeddings

Contextualized Word Embeddings

Convolutional Neural Networks

Basic CNN

Sentence Modeling

Window Approach

Applications

Recurrent Neural Networks

Need for Recurrent Networks

RNN models

Simple RNN

Long Short-Term Memory

Gated Recurrent Units

Applications

RNN for word-level classification

RNN for sentence-level classification

RNN for generating language

Attention Mechanism

Parallelized Attention: The Transformer

Recursive Neural Networks

Basic model

Deep Reinforced Models and Deep Unsupervised Learning

Reinforcement learning for sequence generation

Unsupervised sentence representation learning

Deep generative models

Memory-Augmented Networks

Performance of Different Models on Different NLP Tasks

POS tagging

Parsing

Named-Entity Recognition

Semantic Role Labeling

Sentiment Classification

Machine Translation

Question Answering

Dialogue Systems

Contextualized Embeddings

github地址：https://github.com/omarsar/nlp_overview