A summary on the Pathways Language Model by Google AI, with the good and not-so-good implications — The release of the Pathways Language Model (PaLM) by Google AI has once again led to that familiar, vapid feeling among the AI community— “Oh no, not another large-scale language model that thinks it can learn grammar and human intent”. Just another scaling-up exercise where we throw a bunch of…

A comparison of Flask, Plotly Dash and Streamlit to build dashboards that provide LIME explanations for classification results — In an earlier post, I described how to explain a fine-grained sentiment classifier’s results using LIME ( Local Interpretable Model-agnostic Explanations). To recap, the following six models were used to make fine-grained sentiment class predictions on the Stanford Sentiment Treebank (SST-5) dataset.

How we successfully integrated Dash (by Plotly) into our NLP and linguistics research to study women’s portrayal in mainstream Canadian news — Background Over the last several months, I’ve been working at the Discourse Processing Lab at Simon Fraser University (under the leadership of Dr. Maite Taboada), where we’ve been actively developing and extending the Gender Gap Tracker, an automated Natural Language Processing (NLP) system that measures men and women’s voices on seven…

Tips and tricks to significantly speed up text preprocessing in spaCy using custom pipelines and joblib — Consider you have a large text dataset on which you want to apply some non-trivial NLP transformations, such as stopword removal followed by lemmatizing the words (i.e. reducing them to root form) in the text. spaCy is an industrial-strength NLP library designed for just such a task. In this post…

Hands-on transfer learning using a pretrained transformer in PyTorch — This is Part 3 of a series on fine-grained sentiment analysis in Python. Parts 1 and 2 covered the analysis and explanation of six different classification methods on the Stanford Sentiment Treebank fine-grained (SST-5) dataset. …

In this post, we’ll generate explanations for various classification results for fine-grained sentiment using LIME — “Why Should I Trust You?” — Ribeiro et al. This is Part 2 of a series on fine-grained sentiment analysis in Python. Part 1 covered how to train and evaluate various fine-grained sentiment classifiers in Python. …

In this post, we’ll evaluate and compare the results of several text classification results for the 5-class Stanford Sentiment Treebank (SST-5) dataset. — “Learning to choose is hard. Learning to choose well is harder. And learning to choose well in a world of unlimited possibilities is harder still, perhaps too hard.” — Barry Schwartz When starting a new NLP sentiment analysis project, it can be quite an overwhelming task to narrow down on…

An essay to bring to your Attention the recent developments in generative modelling. — Prashanth Rao and Andrew Wesson Over the years, computers have become increasingly sophisticated in their ability to identify more and more complex patterns. …

A comparison of two transfer learning methods in Natural Language Processing: “ULMFiT” and “OpenAI GPT” for a multi-class classification task involving Twitter data — 2018 has been a hugely exciting year in the field of Natural Language Processing (NLP), in particular, for transfer learning — a technique where instead of training a model from scratch, we use models pre-trained on a large dataset and then fine-tune them for specific natural language tasks. …