University of Cambridge > Talks.cam > Language Technology Lab Seminars > Training for Deployment: Methods for Small and Efficient NLP

  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

ℹ️ Information

Training for Deployment: Methods for Small and Efficient NLP

Download to your calendar using vCal

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

Natural language models for translation and classification work relatively well, or at least well enough that there is demand for widespread use in real systems. Models developed for research however do not naturally translate to deployment scenarios, particularly on resource constrained devices like mobile phones. In this talk I will discuss two axes that make it difficult to deploy NLP models in practice: a) Serial generation in translation models makes them difficult to optimize, and b) Fine-tuned parameter size in classification makes models difficult to deploy to end-users. I propose two approaches that aim to circumvent these issues, and discuss some practical work on deploying large NLP models on edge devices.

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

Herchel Smith Building for Brain and Mind Sciences, Forvie Site, Addenbrooke’s Hospital in Cambridge (unless otherwise stated) For directions see: http://maps.google.co.uk/maps/ms?ie=UTF8&hl=en&msa=0&msid=103610261172628577320.00046a58fcb8a7 The Abdus Salam Lecture Jesus College

Other talks

Secrets of the Surface: The Mathematical Vision of Maryam Mirzakhani ( EDI Film Screening) Morning Break Toward affordable preventive healthcare Talk title TBC Title to be confirmed Using Light for Cancer Detection
 

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