Visual Disambiguation of Preprositional Phrase Attachments : Multimodal Machine Learning for Syntactic Analysis Correction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Visual Disambiguation of Preprositional Phrase Attachments : Multimodal Machine Learning for Syntactic Analysis Correction

Résumé

Prepositional phrase attachments are known to be an important source of errors in parsing natural language. In some cases, pure syntactic features cannot be used for prepositional phrase attachment disambiguation while visual features could help. In this work, we are interested in the impact of the integration of such features in a parsing system. We propose a correction strategy pipeline for prepositional attachments using visual information, trained on a multimodal corpus of images and captions. The evaluation of the system shows us that using visual features allows, in certain cases, to correct the errors of a parser. It also helps to identify the most difficult aspects of such integration.
Fichier principal
Vignette du fichier
IWANN_2019.pdf (1.41 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02465051 , version 1 (10-04-2020)

Identifiants

Citer

Sebastien Delecraz, Leonor Becerra-Bonache, Alexis Nasr, Frédéric Bechet, Benoit Favre. Visual Disambiguation of Preprositional Phrase Attachments : Multimodal Machine Learning for Syntactic Analysis Correction. IWANN: International Work-Conference on Artificial Neural Networks, Jun 2019, Gran Canaria, Spain. ⟨10.1007/978-3-030-20521-8_52⟩. ⟨hal-02465051⟩
67 Consultations
140 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More