Extracting meaning from text

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

• Professor Ann Copestake, Computer Laboratory
• Friday 25 May 2012, 18:00-19:15
• Old Combination Room (OCR), Wolfson College.

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 series.

This talk is included in these lists:

• Chris Davis' list
• Featured lists
• Featured talks
• Guy Emerson's list
• Old Combination Room (OCR), Wolfson College
• Wolfson College Science Society
• Wolfson College Talks & Events
• custom

Note that ex-directory lists are not shown.