University of Cambridge > Talks.cam > NLIP Seminar Series > Semiring Parsing without Parsing

Semiring Parsing without Parsing

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

If you have a question about this talk, please contact Laura Rimell.

Machine translation, summarization, and parsing under most formalisms are examples of what is now popularly known as structured prediction. Semiring parsing is an algorithmic framework that elegantly describes structured problems: it combines deductive logic and probability, cleanly separating model specification from statistical inference via generic dynamic programming algorithms. However, two popular ingredients of modern NLP systems are missing from the semiring parsing abstraction: non-local features and approximate inference. I’ll talk about extending to semiring parsing to include these concepts, including the case in which we don’t use dynamic programming at all.

This talk is part of the NLIP Seminar Series 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