Towards Understanding Situated Natural Language - Archive ouverte HAL Access content directly
Conference Papers Year : 2010

Towards Understanding Situated Natural Language

Abstract

We present a general framework and learning algorithm for the task of concept labeling: each word in a given sentence has to be tagged with the unique physical entity (e.g. person, object or location) or abstract concept it refers to. Our method allows both world knowledge and linguistic information to be used during learning and prediction. We show experimentally that we can learn to use world knowledge to resolve ambiguities in language, such as word senses or reference resolution, without the use of handcrafted rules or features.
Fichier principal
Vignette du fichier
bordes10aistats.pdf (249.18 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-00750937 , version 1 (12-11-2012)

Identifiers

  • HAL Id : hal-00750937 , version 1

Cite

Antoine Bordes, Nicolas Usunier, Ronan Collobert, Jason Weston. Towards Understanding Situated Natural Language. 13th International Conference on Artificial Intelligence and Statistics, May 2010, Chia Laguna Resort, Sardinia, Italy. pp.65-72. ⟨hal-00750937⟩
91 View
126 Download

Share

Gmail Facebook Twitter LinkedIn More