While there’s a lot of work done on defining guidelines and policies for Responsible AI, there are far fewer that data scientists can apply today to build safe, fair, and robust models. This session introduces the open-source nlptest library, which provides a comprehensive solution to testing NLP models before taking them to production.The library supports the full lifecycle of automatically generating tests, editing them, running them, evaluating pass/fail criteria, and generating augmented data to improve models. The nlptest library currently supports testing Spark NLP, Hugging Face, and spaCy models and is designed for extensibility for testing more NLP libraries and tasks.This session will show you what problems the nlptest library solves, how to get things done, and how to extend it.
Sentence embeddings are a powerful tool in natural language processing that helps analyze and understand language. Transformers, a type of neural network architecture, are a popular method for generating these...
Rule-based sentiment analysis in Natural Language Processing (NLP) is a method of sentiment analysis that uses a set of manually-defined rules to identify and extract subjective information from text data....
Almost 90% of the machine learning models encounter delays and never make it into production. Likewise, almost 80% of AI/ML projects stall at some stage before deployment. Developing a machine...
Visual question answering (VQA), an area that intersects the fields of Deep Learning, Natural Language Processing (NLP) and Computer Vision (CV) is garnering a lot of interest in research circles....
Recently, a market research company was conducting a study on customer satisfaction in the travel industry. They had a vast amount of data to analyze, including travel reviews from TripAdvisor....
See More