Natural Language Processing

Overview

We are interested about alternative tools applicable to natural language processing. We also would like to focus on the textual classification problem in low-resource languages and environments. Our specific target here is to:

• study theoretical understanding of the NLP and explore alternative approaches for low-resource NLP

• read and understand scientific papers related to NLP concepts and applications

• learn the effective ways to communicate between disciplines for future interdisciplinary projects.

NLP books and courses

• Natural Language Processing with Dan Jurafsky and Chris Manning

• NLP in UIUC

• Stanford NLP

• Natural Language Processing with Deep Learning

Review Papers and Tutorials

• Deep Learning Based Text Classification A Comprehensive Review

• A Survey of the Usages of Deep Learning for Natural Language Processing

• A primer on deep learning in genomics

Attention Mechanism in NLP

• An Introductory Survey on Attention Mechanisms in NLP Problems

• Understanding Attention for Text Classification

• Attention-Based Bidirectional Long Short Term Memory Networks for Relation Classification

• Attention-based LSTM for Aspect-level Sentiment Classification

Low-resource NLP

• A Survey on Recent Approaches for Natural Language Processing in Low Resource Scenarios

Data Augmentation

• EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks

• A Survey of Data Augmentation Approaches for NLP

Different Approaches for NLP

• A Maximum Entropy Approach to Natural Language Processing

• Bidirectional LSTM-CRF Models for Sequence Tagging

• Hidden Markov Models

• Discriminative Training Methods for Hidden Markov Models

• Text Summarization via Hidden Markov Models and Pivoted QR Matrix Decomposition