University of Cambridge > Talks.cam > NLIP Seminar Series > A Tale of Two Parsers: investigating and combining graph-based and transition-based dependency parsing using beam-search

  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

A Tale of Two Parsers: investigating and combining graph-based and transition-based dependency parsing using beam-search

Download to your calendar using vCal

If you have a question about this talk, please contact Johanna Geiss .

Graph-based and transition-based approaches to dependency parsing adopt very different views of the problem, each view having its own strengths and limitations. We study both approaches under the framework of beam-search. By developing a graph-based and a transition-based dependency parser, we show that a beam-search decoder is a competitive choice for both methods. More importantly, we propose a beam-search-based parser that combines both graph-based and transition-based parsing into a single system for training and decoding, showing that it outperforms both the pure graph-based and the pure transition-based parsers. Testing on the English and Chinese Penn Treebank data, the combined system gave state-of-the-art accuracies of 92.1% and 86.2%, respectively. Authors: Yue Zhang and Stephen Clark

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

in person & via zoom The Lecture Theatre, Floor 2 Ray Dolby Centre Lecture Theatre 2

Other talks

TBC Group Work Cambridge Reading Group on Reproduction: Professor Sara Brill title abstract tbc Royal Papworth Hospital and Acute Medicine Quantum graphs with a time asymmetry: spectral optimization and spectral statistics
 

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