Boosting for Efficient Model Selection for Syntactic Parsing

Abstract : We present an efficient model selection method using boosting for transition-based constituency parsing. It is designed for exploring a high-dimensional search space, defined by a large set of feature templates, as for example is typically the case when parsing morphologically rich languages. Our method removes the need to manually define heuristic constraints, which are often imposed in current state-of-the-art selection methods. Our experiments for French show that the method is more efficient and is also capable of producing compact, state-of-the-art models.
Document type :
Conference papers
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01391743
Contributor : Rachel Bawden <>
Submitted on : Thursday, December 22, 2016 - 3:55:04 PM
Last modification on : Saturday, May 4, 2019 - 1:20:01 AM
Long-term archiving on : Tuesday, March 21, 2017 - 5:48:43 AM

File

bawden_crabbe_2016_coling.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01391743, version 2

Citation

Rachel Bawden, Benoît Crabbé. Boosting for Efficient Model Selection for Syntactic Parsing. COLING 2016 - 26th International Conference on Computational Linguistics, Dec 2016, Osaka, Japan. pp.1-11. ⟨hal-01391743v2⟩

Share

Metrics

Record views

549

Files downloads

420