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

  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

Semiring Parsing without Parsing

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

St. Columba's Hall, Downing Place (off Downing Street, close to the new John Lewis) Webinar & FW11, Computer Laboratory, William Gates Building. Satellite

Other talks

Shape modes of CP^1 vortices Clonal haematopoiesis, early detection and pre-leukemia to leukemia development Atmospheric Methane - rise, surge, and ongoing post-surge growth. Can we mitigate the rise, and can anything be done to reduce emissions? Title tbc The Inaccessible Game Title to be confirmed
 

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