University of Cambridge > Talks.cam > NLIP Seminar Series > Chinese CCGbank: Deep derivations and dependencies for Chinese CCG parsing

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Chinese CCGbank: Deep derivations and dependencies for Chinese CCG parsing

Download to your calendar using vCal

If you have a question about this talk, please contact Tamara Polajnar .

We adapt the corpus conversion methodology harnessed by Hockenmaier for CCGbank, to obtain Chinese CCGbank, the first wide-coverage CCG corpus of Chinese text.

We show that the corpus conversion methodology, and thus Chinese CCGbank, is appropriate for acquiring wide-coverage models of Chinese syntax, by adapting three state-of-the-art Chinese parsers to obtain the first Chinese CCG parsing models in the literature.

We demonstrate that while the three parsers are only separated by a small margin trained on English CCGbank, a substantial gulf of 4.8% separates the same parsers trained on Chinese CCGbank. We also confirm that the gap between the states-of-the-art in English and Chinese PSG parsing can be observed in CCG parsing.

Our parsing experiments establish Chinese CCG parsing as a new and substantial challenge.

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

Dept Chemical Engineering and Biotechnology, Philippa Fawcett Drive CB3 OAS (Lecture Theatre 1) Average on weekdays: 8933.26756757 kWh Senior Parlour, Gonville & Caius College

Other talks

Quantum optics with organic molecules Early cancer clinical trials Discussion II CSAR lecture: In a post-Ozempic world, have we cured obesity? Advances in Label-Free High-Resolution Molecular Imaging using J Series III Cluster SIMS Group Work
 

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