University of Cambridge > Talks.cam > Language Technology Lab Seminars > Sentence Generation using a Dynamic Canvas

  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

Sentence Generation using a Dynamic Canvas

Download to your calendar using vCal

If you have a question about this talk, please contact Dimitri Kartsaklis .

I will discuss the Attentive Unsupervised Text Writer (AUTR), a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct sentences. By viewing the state of the memory at intermediate stages and where the model is placing its attention, we gain insight into how it constructs sentences. We demonstrate that AUTR learns a useful latent representation for each sentence and achieves competitive log-likelihood lower bounds whilst being computationally efficient. It is effective at generating and reconstructing sentences, as well as imputing missing words.

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

Room 101, Sir William Hardy Building provisionally in Room 215 at Cambridge Research Institute (TBC!). Department of Plant Sciences, Large Lecture Theatre

Other talks

Coming soon Group Work "That's History. That's Truth. I Seen It Myself": T'tc~tsa (Wailaki) and the Enslavement of California Native Americans. Cambridge AI in Medicine Seminar - July 2026 Talk title TBC Discussion II
 

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