University of Cambridge > Talks.cam > Wolfson College Science Society talks > Extracting meaning from text

Extracting meaning from text

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

If you have a question about this talk, please contact Dr Xavier Moya.

One of the main long-term goals of automatic human language processing has been to produce computationally-tractable representations of what a text means. This includes determining the relationships between entities and events mentioned explicitly (e.g., `who did what to whom’), working out some of the implicit content (e.g., which `Clinton’ are we talking about) and making inferences (e.g., if X assassinated Y, then X killed Y – unless `assassinate’ is being used metaphorically). I’ll outline some of the technology we’re investigating to address some of these tasks on a large scale and describe how the results can be used in applications. With the aid of some computer-generated poetry, I’ll also show that these techniques can reveal surprising aspects of language use.

This talk is part of the Wolfson College Science Society talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity