Slideshare (6): Cross-lingual Paper reading notes

During this summer, I did a project on cross-lingual NLP tasks. Recently I was working my notes and I organized them into a better format. I would like to share some of the notes with the readers who might be interested in this topic.

Cross_lingual_NLP(PDF)

Papers covered:

Deep Learning 17: text classification with BERT using PyTorch

Why BERT

If you are a big fun of PyTorch and NLP, you must try to use the PyTorch based BERT implementation! If you have your own dataset and want to try the state-of-the-art model, BERT is a good choice.
Please check the code from https://github.com/huggingface/pytorch-pretrained-BERT to get a close look. However, in this post, I will help you to apply pre-trained BERT model on your own data to do classification. Continue reading “Deep Learning 17: text classification with BERT using PyTorch”

Resources for BioNLP: datasets and tools

Corpora for general medical texts

Open Research Corpus

Over 39 million published research papers in Computer Science, Neuroscience, and Biomedical.
Full dataset 36G, not restricted.

Working with ROUGE 1.5.5 Evaluation Metric in Python

If you use ROUGE Evaluation metric for text summarization systems or machine translation systems, you must have noticed that there are many versions of them. So how to get it work with your own systems with Python? What packages are helpful? In this post, I will give some ideas based on engineering’s view (which means I am not going to introduce what is ROUGE). I also suffered from few issues and finally got them solved. My methods might not be the best ways but they worked.

NLP 05: From Word2vec to Doc2vec: a simple example with Gensim

Introduction

First introduced by Mikolov 1 in 2013, the word2vec is to learn distributed representations (word embeddings) when applying neural network. It is based on the distributed hypothesis that words occur in similar contexts (neighboring words) tend to have similar meanings. Two models here: cbow ( continuous bag of words) where we use a bag of words to predict a target word and skip-gram where we use one word to predict its neighbors. For more, although not highly recommended, have a look at TensorFlow tutorial here. Continue reading “NLP 05: From Word2vec to Doc2vec: a simple example with Gensim”

NLP 04: Log-Linear Models for Tagging Task (Python)

We will focus on POS tagging in this blog.

Notations

While HMM gives us a joint probability on tags and words: $p({t}_{[1:n]},{w}_{[1:n]})$. Tags t and words w are one-to-one mapping, so in the series, they share the same length.