A list of NLP(Natural Language Processing) tutorials built on PyTorch and keras.
A step-by-step tutorial on how to implement and adapt to the simple real-word NLP task.
-
Neural Machine Translation: This repo provides a simple PyTorch implementation of Neural Machine Translation, along with an intrinsic/extrinsic comparison of various sequence-to-sequence (seq2seq) models in translation.
Keyword: sequence to seqeunce network(seq2seq), Attention, Auto-regressive, Teacher-forcing -
Question-Answer Matching: This repo provides a simple PyTorch implementation of Question-Answer matching. Here we use the corpus from Stack Exchange in English to build embeddings for entire questions. Using those embeddings, we find similar questions for a given question, and show the corresponding answers to those I found.
Keyword: LSTM with variable-length seqeucnes, TF-IDF, Text classification -
News Category Classification: This repo contains a simple source code for text-classification based on TextCNN. Corpus is Huffpost news category dataset in English. Most open sources are a bit difficult to study & make text-classification model for beginners. So, I hope that this repo can be a good solution for people who want to have their own text-classification model.
Keyword: TextCNN, Text classification, Text cateogrization -
Movie Rating Classification (Korean NLP): This repo contains a simple source code for text-classification based on TextCNN. Corpus is movie review dataset in the Korean language. Most open sources are a bit difficult to study & make text-classification model for beginners. So, I hope that this repo can be a good solution for people who want to have their own text-classification model.
Keyword: TextCNN, Text classification, Sentiment analysis -
Question Answering for SQuAD (working)