A
Ann Yuan
Researcher at Google
Publications - 16
Citations - 772
Ann Yuan is an academic researcher from Google. The author has contributed to research in topics: Computer science & Language model. The author has an hindex of 5, co-authored 10 publications receiving 463 citations.
Papers
More filters
Proceedings Article
Visualizing and Measuring the Geometry of BERT
TL;DR: This article found evidence of a fine-grained geometric representation of word senses in BERT and presented empirical descriptions of syntactic representations in both attention matrices and individual word embeddings as well as a mathematical argument to explain the geometry of these representations.
Posted Content
Visualizing and Measuring the Geometry of BERT
TL;DR: This paper describes qualitative and quantitative investigations of one particularly effective model, BERT, and finds evidence of a fine-grained geometric representation of word senses in both attention matrices and individual word embeddings.
Posted Content
TensorFlow.js: Machine Learning for the Web and Beyond
Daniel Smilkov,Nikhil Thorat,Yannick Assogba,Ann Yuan,Nick Kreeger,Ping Yu,Kangyi Zhang,Shanqing Cai,Eric Nielsen,David A W Soergel,Stan Bileschi,Michael Terry,Charles Nicholson,Sandeep N. Gupta,Sarah Sirajuddin,D. Sculley,Rajat Monga,Greg S. Corrado,Fernanda B. Viégas,Martin Wattenberg +19 more
TL;DR: The design, API, and implementation of TensorFlow.js is described, providing a set of APIs that are compatible with those in Python, allowing models to be ported between the Python and JavaScript ecosystems.
Proceedings ArticleDOI
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
Ian Tenney,James Wexler,Jasmijn Bastings,Tolga Bolukbasi,Andy Coenen,Sebastian Gehrmann,Ellen Jiang,Mahima Pushkarna,Carey Radebaugh,Emily Reif,Ann Yuan +10 more
TL;DR: The Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models, is presented, which integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface to enable rapid exploration and error analysis.
Proceedings ArticleDOI
Wordcraft: Story Writing With Large Language Models
TL;DR: This work built Wordcraft, a text editor in which users collaborate with a generative language model to write a story, and shows that large language models enable novel co-writing experiences.