Evaluation of Dependency Parsers on Unbounded Dependencies

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

• Laura Rimell - University of Cambridge
• Wednesday 28 July 2010, 12:00-12:30
• GS15, Computer Laboratory.

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

Joint work with Joakim Nivre, Ryan McDonald and Carlos Gómez-Rodríguez.

We evaluate two dependency parsers, MST Parser and MaltParser, with respect to their capacity to recover unbounded dependencies in English, a type of evaluation that has been applied to grammar-based parsers and statistical phrase structure parsers but not to dependency parsers. The evaluation shows that when combined with simple post-processing heuristics, the parsers correctly recall unbounded dependencies roughly 50% of the time, which is only slightly worse than two grammar-based parsers specifically designed to cope with such dependencies.

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
• GS15, 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.