Correcting prepositional phrase attachments using multimodal corpora

Abstract : PP-attachments are an important source of errors in parsing natural language. We propose in this article to use data coming from a multimodal corpus, combining tex-tual, visual and conceptual information, as well as a correction strategy, to propose alternative attachments in the output of a parser.
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01693292
Contributor : Sebastien Delecraz <>
Submitted on : Friday, January 26, 2018 - 10:01:47 AM
Last modification on : Monday, March 4, 2019 - 2:04:14 PM
Document(s) archivé(s) le : Friday, May 25, 2018 - 3:15:59 AM

File

iwpt2017_vision.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01693292, version 1

Collections

Citation

Sebastien Delecraz, Alexis Nasr, Frédéric Béchet, Benoit Favre. Correcting prepositional phrase attachments using multimodal corpora. The 15th International Conference on Parsing Technologies, Sep 2017, Pise, Italy. ⟨hal-01693292⟩

Share

Metrics

Record views

150

Files downloads

26