Our research encompasses all aspects of speech and language processing—ranging from the design of fundamental machine learning methods to the design of advanced applications that can extract information from documents, translate between languages, and execute instructions in real-world environments. Two central themes of our research are unsupervised discovery of linguistic structure (from sounds to word meanings to grammars) and the use of language to train and explain computational models across application domains (including computer vision, robotics, and medicine). We aim to simultaneously tackle pressing social problems and develop foundational technologies for enabling humans to interact with computers using the languages they already speak.
Latest news in natural language and speech processing
By allowing users to clearly see data referenced by a large language model, this tool speeds manual validation to help users spot AI errors.
The approach can detect anomalies in data recorded over time, without the need for any training.
Ranking at the top for the 13th year in a row, the Institute also places first in 11 subject areas.
Associate Professor Jonathan Ragan-Kelley optimizes how computer graphics and images are processed for the hardware of today and tomorrow.
The Institute also ranks second in five subject areas.