A tutorial on how to summarize text and generate features from Github Issues using deep learning with Keras and TensorFlow. By Hamel Husain Teaser: Training a model to summarize Github Issues The above results are randomly selected elements of a holdout set. Keep reading below, there will be a link to many more examples!

How to use pre-trained English language models from Hugging Face on non-English texts — A pre-trained model is a saved machine learning model that was previously trained on a large dataset (e.g all the articles in the Wikipedia) and can be later used as a “program” that carries out an specific task (e.g finding the sentiment of the text). Hugging Face is a great…

Spelling correction is an important task in NLP for data cleaning and preparing for using ML models. There are many libraries in python that you can use to make auto spelling correction to strings in python, in this article, I’ll show you the most popular libraries and how to use…

In this tutorial, instead of training from scratch, we will see how to fine-tune in just over a day, on one GPU and with a little more than 1GB of training data an English pre-trained transformer-based language model to any another language. As a practical case, we fine-tune to Portuguese…

Easily rectify your spelling mistakes using Python — Type in “Stendford University” on your search engine and you will notice that it provides you with results for “Standford University”. …

Table of contents Introduction Why Grammatical Error Correction (GEC) Formulating as Business Problem Formulating as ML/DL Problem Literature Survey Dataset Overview Data Analysis/ Exploratory Data Analysis Data Preparation Baseline models. Attention Mechanism Model Training statistics Model output Results Inference Future work Github repository 1. Introduction Grammatical error correction (GEC), as the name suggests is the…

¿Qué es la distancia de Levenshtein? Supongamos que vamos a escribir la palabra algoritmo, pero hemos cometido algunos errores y en su lugar escribimos algtratmo. ¿Cuál es el número mínimo de operaciones (eliminaciones, inserciones o sustituciones) requeridas para que algtratmo sea igual a algoritmo. Si x=algtratmo y z=algoritmo: DL(x,z)=2, ya…

Building a deep Transformer Network that corrects English sentences — I am a big fan of services like Grammarly or Reverso that can help correct grammar and spelling errors. This motivated me to build a much simpler machine learning baseline that can automatically correct English sentences. In this post, we will go through the implementation and training of a Sequence-To-Sequence…

Development of NLP-related solutions is gaining momentum. Thanks to the squad of pre-trained models based on the Transformer, BERT and GPT architecture, NLP-related tasks, Grammatical Error Correction (GEC) tasks, in particular, can be completed super efficiently. In this story I’d like to tell about WebSpellChecker approach to GEC. We developed…

Text Processing is one of the most common task in many ML applications. Below are some examples of such applications. • Language Translation: Translation of a sentence from one language to another. • Sentiment Analysis: To determine, from a text corpus, whether the sentiment towards any topic or product…