Cross-situational noun and adjective learning in an interactive scenario - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Cross-situational noun and adjective learning in an interactive scenario

Abstract

Learning word meanings during natural interaction with a human faces noise and ambiguity that can be solved by analysing regularities across different situations. We propose a model of this cross-situational learning capacity and apply it to learning nouns and adjectives from noisy and ambiguous speeches and continuous visual input. This model uses two different strategy: a statistical filtering to remove noise in the speech part and the Non Negative Matrix Factorization algorithm to discover word-meaning in the visual domain. We present experiments on learning object names and color names showing the performance of the model in real interactions with humans, dealing in particular with strong noise in the speech recognition.
Fichier principal
Vignette du fichier
Chen_ICDL15_final.pdf (1.54 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01170674 , version 1 (18-08-2015)

Identifiers

  • HAL Id : hal-01170674 , version 1

Cite

Yuxin Chen, David Filliat. Cross-situational noun and adjective learning in an interactive scenario. Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Aug 2015, Providence, United States. ⟨hal-01170674⟩
141 View
238 Download

Share

Gmail Mastodon Facebook X LinkedIn More