Tree topological features for unlexicalized parsing
Refereed conference paper presented and published in conference proceedings


Full Text

Times Cited

Other information
AbstractAs unlexicalized parsing lacks word token information, it is important to investigate novel parsing features to improve the accuracy. This paper studies a set of tree topological (TT) features. They quantitatively describe the tree shape dominated by each non-terminal node. The features are useful in capturing linguistic notions such as grammatical weight and syntactic branching, which are factors important to syntactic processing but overlooked in the parsing literature. By using an ensemble classifierbased model, TT features can significantly improve the parsing accuracy of our unlexicalized parser. Further, the ease of estimating TT feature values makes them easy to be incorporated into virtually any mainstream parsers.
All Author(s) ListChan S.W.K., Cheung L.Y.L., Chong M.W.C.
Name of Conference23rd International Conference on Computational Linguistics, Coling 2010
Start Date of Conference23/08/2010
End Date of Conference27/08/2010
Place of ConferenceBeijing
Country/Region of ConferenceChina
Detailed descriptionorganized by Chinese Information Processing Society of China,
Year2010
Month12
Day1
Volume Number2
Pages117 - 125
LanguagesEnglish-United Kingdom

Last updated on 2020-04-07 at 01:03