University of Cambridge > Talks.cam > Language Technology Lab Seminars > Learning to Generate Textual Data

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹī¸ Information

Learning to Generate Textual Data

Download to your calendar using vCal

If you have a question about this talk, please contact Mohammad Taher Pilehvar .

To learn text understanding models with millions of parameters one needs massive amounts of data. In this work, we argue that generating data can compensate for this need. While defining generic data generators is difficult, we propose to allow generators to be “weakly” specified in the sense that a set of parameters controls how the data is generated. Consider for example generators where the example templates, grammar, and/or vocabulary is determined by this set of parameters. Instead of manually tuning these parameters, we learn them from the limited training data at our disposal. To achieve this, we derive an efficient algorithm called GeneRe that jointly estimates the parameters of the model and the undetermined generation parameters. We illustrate its benefits by learning to solve math exam questions using a highly parametrised sequence-to-sequence neural network.

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

Average on weekdays: 9055.33616692 kWh Linnett Room, Robinson College TBC West Cambridge

Other talks

Harnessing Radical Reactivity for Molecular Innovation Discussion I C2D3 Computational Biology Annual Symposium 2026 LMB Seminar - Mechanisms of mRNA packaging and export From lab to clinic: an introduction to translational research "Green" RSEs? A new role (and a new community) to reduce the environmental impact of research
 

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