University of Cambridge > Talks.cam > Language Technology Lab Seminars > Efficient sentence encoders for Conversational AI in the industry

Efficient sentence encoders for Conversational AI in the industry

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Marinela Parovic.

Building real-world conversational AI applications requires resource-efficient models that can learn in low-data regimes with only a handful of annotated examples. Fully fine-tuning large pretrained language models is expensive and computationally intractable for these applications, where fast-paced development cycles are necessary. This talk presents ConveRT and ConVEx; effective, affordable, quick-to-train, and quick-to-fine-tune sentence encoders that work well in such few-shot low-data scenarios. These encoders achieve state-of-the-art performance across a wide range of conversational tasks such as response selection, intent classification and value extraction, offering quick and effective adaptation to new tasks, domains, and languages.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity