Neural Greedy Constituent Parsing with Dynamic Oracles

Maximin Coavoux 1, * Benoît Crabbé 1
* Corresponding author
Abstract : Dynamic oracle training has shown substantial improvements for dependency parsing in various settings, but has not been explored for constituent parsing. The present article introduces a dynamic oracle for transition-based constituent parsing. Experiments on the 9 languages of the SPMRL dataset show that a neural greedy parser with morphological features , trained with a dynamic oracle, leads to accuracies comparable with the best non-reranking and non-ensemble parsers.
Keywords : NLP parsing
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-01353734
Contributor : Benoit Crabbe <>
Submitted on : Wednesday, August 17, 2016 - 5:09:11 PM
Last modification on : Friday, January 4, 2019 - 5:33:38 PM
Long-term archiving on : Friday, November 18, 2016 - 10:06:59 AM

File

P16-1017.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01353734, version 1

Collections

Citation

Maximin Coavoux, Benoît Crabbé. Neural Greedy Constituent Parsing with Dynamic Oracles. Association for Computational Linguistics (ACL), 2016, Berlin, Germany. ⟨hal-01353734⟩

Share

Metrics

Record views

216

Files downloads

312