Hate Speech Detection on Dynabench

Hate Speech Detection with Transformers

tl;dr A step-by-step tutorial to train a hate speech detection model to classify text containing hate speech. The trained model has a BERT-based transformer architecture. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

January 6, 2021 · 7 min · Eugene
Biology NER with BioBERT to Extract Diseases and Chemicals.

Biology Named Entity Recognition with BioBERT

tl;dr A step-by-step tutorial to train a BioBERT model for named entity recognition (NER), extracting diseases and chemical on the BioCreative V CDR task corpus. Our model is #3-ranked and within 0.6 percentage points of the state-of-the-art. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

December 30, 2020 · 6 min · Eugene
Named Entity Recognition with BERT in Mandarin

Named Entity Recognition with BERT in Mandarin

tl;dr A step-by-step tutorial to train a state-of-the-art model with BERT for named entity recognition (NER) in mandarin, 中文命名实体识别. Our model beats the state-of-the-art by 0.7 percentage points. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

December 24, 2020 · 6 min · Eugene
Named Entity Recognition on Weibo in Mandarin

Named Entity Recognition on Weibo in Mandarin

tl;dr A step-by-step tutorial to train a state-of-the-art model with flair and BERT for named entity recognition (NER) in mandarin, 中文命名实体识别, on a Weibo dataset. Our model beats the state-of-the-art by 20+ percentage points. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

December 24, 2020 · 6 min · Eugene
Sentiment Analysis in Mandarin on Food Delivery Reviews

Sentiment Analysis in Mandarin with XLNet

tl;dr A step-by-step tutorial to train a state-of-the-art model for sentiment analysis on mandarin food delivery reviews using the XLNet architecture. We will use Google Colab’s free Jupyter Notebook in the cloud. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

December 23, 2020 · 6 min · Eugene
Named Entity Recognition (NER) Model Using FLAIR

Train a Named Entity Recognition (NER) Model Using FLAIR

tl;dr A step-by-step tutorial to train a state-of-the-art model for named entity recognition (NER), the task of identifying persons, organizations and locations from a piece of text. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

December 23, 2020 · 5 min · Eugene
Sentiment Analysis on Movie Reviews

Sentiment Analysis on Movie Reviews with XLNet

tl;dr A step-by-step tutorial to train a sentiment analysis model to classify polarity of IMDB movie reviews with XLNet using a free Jupyter Notebook in the cloud. The IMDB Movie Reviews Dataset and XLNet The Internet Movie Database (IMDb) movie reviews dataset is a very well-established benchmark (since 2011) for sentiment analysis performance. It’s probably the first large-ish (50,000 train+test), balanced sentiment analysis dataset, making it a very nice dataset for benchmarking on....

December 22, 2020 · 7 min · Eugene
Sarcasm Detection on Tweets

Learn to Train a State-of-the-Art Model for Sarcasm Detection

tl;dr A step-by-step tutorial to train a state-of-the-art model to detect sarcasm 🙄 from tweets with a free Jupyter Notebook in the cloud. Sooo Impressive Sarcasm Detection Model on Tweets Recently Venture Beat published (and Communications of the ACM referenced) a news article titled “AI researchers made a sarcasm detection model and it’s sooo impressive” which detailed how researchers from China had come up with a “sarcasm detection AI” that “achieved state-of-the-art performance on a dataset drawn from Twitter”....

December 22, 2020 · 10 min · Eugene
Is Google Colab or Paperspace Gradient better for training ML models in the cloud on free GPUs? We say use both.

Free GPUs for Machine Learning: Google Colab vs Paperspace Gradient

tl;dr Google Colab and Paperspace Gradient both provide Jupyter notebooks with free GPUs in the cloud to code, train and test your ML models. Which is the better option? In this article we compare them. Our final answer is to use both depending on your current ML workloads and requirements. What is Google Colab and what is Paperspace Gradient? If we had to pick one particular tool that makes ML easier for everyone, it would be cloud Jupyter notebooks....

December 17, 2020 · 5 min · Eugene