Abstracts: October 9, 2023

Join Microsoft's research community at the forefront of cutting-edge advances through "Abstracts," a series of short but informative conversations about notable achievements in various fields.

In this episode, Dr. Sheng Zhang, a Senior Researcher at Microsoft Research, discusses the paper "UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition" with host Dr. Gretchen Huizinga. The paper outlines a method for distilling large language models into smaller, more efficient ones to improve named entity recognition, an important task in natural language processing (NLP). By achieving state-of-the-art performance, Zhang and his team's UniversalNER models promise to make NLP more accessible and efficient, especially in specialized areas like biomedicine.

To learn more, check out the project website, demo, and code on GitHub, and take a look at the dataset and models on Hugging Face.

Stay informed and engaged with the latest research in your field with "Abstracts."