University of Cambridge > > Language Technology Lab Seminars > Learning across Adverse Conditions in Natural Language Processing

Learning across Adverse Conditions in Natural Language Processing

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

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

Transferring knowledge to solve a related problem and learning from limited, unreliable inputs are examples of extraordinary human ability. State-of-the-art machine learning models based on deep learning often fail under such adverse conditions. How can we build Natural Language Processing technology which transfer better to new conditions, such as learning to process a new language or a new text domain? Transfer learning (TL) and multi-task learning (MTL) can help remedy this problem. In this talk, I will discuss TL and MTL methods to tackle this challenge and present some of our (on-going) work on NLP for zero-shot and few-shot transfer, including Danish, a case study on a very low-resource dialect and recent work on information extraction for task-oriented dialogue.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


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