An Analysis of Tree Topological Features in Classifier-Based Unlexicalized Parsing
Refereed conference paper presented and published in conference proceedings


Full Text

Times Cited
Web of Science1WOS source URL (as at 28/05/2020) Click here for the latest count

Other information
AbstractA novel set of "tree topological features" (TTFs) is investigated for improving a classifier-based unlexicalized parser. The features capture the location and shape of subtrees in the treebank. Four main categories of TTFs are proposed and compared. Experimental results showed that each of the four categories independently improved the parsing accuracy significantly over the baseline model. When combined using the ensemble technique, the best unlexicalized parser achieves 84% accuracy without any extra language resources, and matches the performance of early lexicalized parsers. Linguistically. TTFs approximate linguistic notions such as grammatical weight, branching property and structural parallelism. This is illustrated by studying how the features capture structural parallelism in processing coordinate structures.
All Author(s) ListChan SWK, Chong MWC, Cheung LYL
Name of Conference12th Annual Conference on Intelligent Text Processing and Computational Linguistics
Start Date of Conference20/02/2011
End Date of Conference26/02/2011
Place of ConferenceTokyo
Country/Region of ConferenceJapan
Journal nameLecture Notes in Artificial Intelligence
Year2011
Month1
Day1
Volume Number6608
PublisherSPRINGER-VERLAG BERLIN
Pages155 - 170
ISBN978-3-642-19399-6
ISSN0302-9743
LanguagesEnglish-United Kingdom
Keywordsmachine learning; parsing; topological features; unlexicalized model
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; Computer Science, Interdisciplinary Applications; Computer Science, Theory & Methods

Last updated on 2020-29-05 at 00:59