Correcting prepositional phrase attachments using multimodal corpora
Résumé
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.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...