University of Cambridge > Talks.cam > Inference Group > Putting Some Language Back Into Language Modelling

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

Putting Some Language Back Into Language Modelling

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

If you have a question about this talk, please contact Emli-Mari Nel.

This is a follow-up of a talk that I gave a few weeks ago . The first half of the talk will cover some improvements that turned a Hierarchical Dirichlet language model with fairly poor predictive performance into a state-of-the-art model. The second part of the talk will be about a new Bayesian language model that combines prior knowledge about English syntax with a semantic (topic) model into a predictive text entry system, which will be demo’ed during the talk.

This talk is part of the Inference Group series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Climate change Part III Seminar Series Lent 2008 Department of Psychiatry talks stream

Other talks

'Politics in Uncertain Times: What will the world look like in 2050 and how do you know? The Warsaw Uprising in Polish Popular Culture after 1989 How language variation contributes to reading difficulties and “achievement gaps” Mechanical performance of wall structures in 3D printing processes: theory, design tools and experiments Title to be confirmed Speculations about homological mirror symmetry for affine hypersurfaces Art and Migration A feast of languages: multilingualism in neuro-typical and atypical populations Unbiased Estimation of the Eigenvalues of Large Implicit Matrices Existence of Lefschetz fibrations on Stein/Weinstein domains Transcription by influenza virus RNA polymerase: molecular mechanisms, cellular aspects and inhibition
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity