University of Cambridge > Talks.cam > NLIP Seminar Series > A computational model of language production

  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

A computational model of language production

Download to your calendar using vCal

If you have a question about this talk, please contact Suchir Salhan .

In this talk, I present a framework that models language production as a mapping from explicit, structured meaning representations to surface sentences. The framework combines an explicit symbolic grammar with unsupervised learning algorithms, allowing us to ask how far structured meaning by itself can drive acquisition. If we view the framework as a computational proxy for language production and acquisition, we can encode different grammatical theories as alternative grammar modules, expose them to the same data, and compare how they learn and process. I will briefly illustrate this with a case study contrasting a lexicalist grammar with a construction-based one, showing how their characteristic behaviours emerge within the same simulation.

Yuan Gao is a PhD Candidate at the University of Cambridge.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Ray Dolby Centre Seminar Room 3 (third floor, access card required) Cambridge Pro Bono Project Lecture Theatre 4, Cambridge University Engineering Department, Trumpington Street, Cambridge CB2 1PZ

Other talks

Title and abstract tba Polar Oceans Seminar Talk The United States of America at 250: Reflections on the Past, Present and Future of Independence Not-so-noble gases, key tracers of Earth’s habitability: what their behaviour in planetary interiors can tell us? The search for a new population of strong gravitational lenses with JWST Animating urbanism: the demotic multiplicities of seeing cities digitally
 

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