An experimental comparison between NMF and LDA for active cross-situational object-word learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

An experimental comparison between NMF and LDA for active cross-situational object-word learning

Abstract

Humans can learn word-object associations from ambiguous data using cross-situational learning and have been shown to be more efficient when actively choosing the learning sample order. Implementing such a capacity in robots has been performed using several models, among which are the latent-topic learning models based on Non-Negative Matrix Factorization and Latent Dirichlet Allocation. We compare these approaches on the same data in a batch and in an incremental learning scenario to analyze their strength and weaknesses and furthermore show that they can be the basis for efficient active learning strategies. The proposed modeling deals with both the referential ambiguity and the noisy linguistic descriptions and is grounding meanings of object's modal features (color and shape) and not only the object identity. The resulting active learning strategy is briefly discussed in comparison with active cross-situational learning of object names performed by humans.
Fichier principal
Vignette du fichier
Chen_ICDL16_final.pdf (2.75 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01370853 , version 1 (23-09-2016)

Identifiers

  • HAL Id : hal-01370853 , version 1

Cite

Yuxin Chen, Jean-Baptiste Bordes, David Filliat. An experimental comparison between NMF and LDA for active cross-situational object-word learning. Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Sep 2016, Cergy-Pontoise, France. ⟨hal-01370853⟩
254 View
1588 Download

Share

Gmail Mastodon Facebook X LinkedIn More