Skip to Main content Skip to Navigation
Conference papers

Can we parse without tagging ?

Abstract : Syntactic parsing is a major area of NLP which has been widely studied with the help of many approaches. Usually, parsers take in input tagged texts, that is to say texts whose lexical units have been annotated with informations such as lemma, grammatical code, gender and number. In this paper, we present a parsing method that can work on untagged texts as well as on tagged ones. We then compare results obtained on specialized texts in their raw and tagged version in order to determine if tagging is absolutely necessary.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal-upec-upem.archives-ouvertes.fr/hal-00636997
Contributor : Guillaume Blin <>
Submitted on : Friday, October 28, 2011 - 7:57:13 PM
Last modification on : Wednesday, February 26, 2020 - 7:06:06 PM
Long-term archiving on: : Monday, January 30, 2012 - 11:18:34 AM

File

ltc_138_fairon.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00636997, version 1

Collections

Citation

Cédrick Fairon, Sébastien Paumier, Patrick Watrin. Can we parse without tagging ?. 2nd Language & Technology Conference (LTC'05), 2005, Poznan, Poland. pp.473-477. ⟨hal-00636997⟩

Share

Metrics

Record views

359

Files downloads

153