Novelty with Transformers and Clustering

Document analysis and understanding is an active area of research in the applied NLP community. In this talk, Alex Cunliffe demonstrates an unsupervised method to organize a body of text into a set of topics and outliers.This approach uses a transformer model that has been fine-tuned for semantic similarity (SentenceTransformers hyperlink: sbert.net). It can be used to quickly review a large set of documents to identify areas of interest or concern without requiring a human to exhaustively read through each document one-by-one. She demonstrates this approach applied to the lyrics of an early-2000s hit musical piece.


Did you find this valuable? Subscribe to our newsletter and get our best content delivered straight to you.

You Might Also Like

Natural Language Generation - What Can You Develop in the Next 3 Years

In this video Justin Pounders, Director of Machine Learning and AI Research at Prolego, breaks down natural language generation (NLG) into its most basic components and describes how you can begin building out these components in your business. (And, no, it doesn’t depend on GPT-3!) He describes how NLG depends critically on two questions (WHAT you want to say and HOW you say it), the types of data you can feed into NLG systems, and a development path for being able to summarize multiple sources of data in plain English.

The critical flaw with AutoML: Big problems require human creativity

Like most engineers, I hate tedious work. That’s why I love the idea of automatic machine learning (AutoML). As much as I want to love AutoML, it’s been incorrectly framed as a substitute for data scientists. This confusion arises from a misunderstanding of what actually happens in machine learning projects.

Novelty with Transformers and Clustering

Document analysis and understanding is an active area of research in the applied NLP community. In this talk, we demonstrate an unsupervised method to organize a body of text into a set of topics and outliers. This approach uses a transformer model that has been fine-tuned for semantic similarity (SentenceTransformers hyperlink: sbert.net). It can be used to quickly review a large set of documents to identify areas of interest or concern without requiring a human to exhaustively read through each document one-by-one. We demonstrate this approach applied to the lyrics of an early-2000s hit musical piece.

Getting started? Get our book!

The complete guide for understanding AI, identifying opportunities, and launching your first product and become an AI Company in 90 days.

  • AI Fundamentals
  • The 4 Product Patterns
  • The AI Canvas
  • Strategy
  • Discovery Opportunities
  • Launching Your First Product
  • Hiring Strategies

Sign up to download our guidebook for CEOs, product people and busy business leaders.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.