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

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Efficient sentence encoders for Conversational AI in the industry

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Wolfson Lecture Hall, Churchill College Paston Brown Room, Homerton College, Hills Road, Cambridge CB2 8PQ Representational Similarity Analysis

Other talks

Online Causal Inference Semina Spectral rigidity of random covers of compact hyperbolic surfaces Emergency Medicine and Metabolic Medicine Christmas Social Evening & Annual General Meeting FILM: One With The Whale Title to be confirmed
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity