Shift-Reduce CCG Parsing with a Dependency Model

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

• Wenduan Xu, University of Cambridge
• Thursday 05 June 2014, 13:00-13:30
• FW26, Computer Laboratory.

If you have a question about this talk, please contact Ekaterina Kochmar.

We present the first dependency model for a shift-reduce CCG parser. Modelling dependencies is desirable for a number of reasons, including handling the “spurious” ambiguity of CCG ; fitting well with the theory of CCG ; and optimizing for structures which are evaluated at test time. We develop a novel training technique using a dependency oracle, in which all derivations are hidden. A challenge arises from the fact that the oracle needs to keep track of exponentially many gold-standard derivations, which is solved by integrating a packed parse forest with the beam-search decoder. Standard CCG Bank tests show the model achieves up to 1.05 labeled F-score improvements over three existing, competitive CCG parsing models.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• FW26, Computer Laboratory
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.