Crossmodal Network-Based Distributional Semantic Models

Elias Iosif, Alexandros Potamianos


Abstract
Despite the recent success of distributional semantic models (DSMs) in various semantic tasks they remain disconnected with real-world perceptual cues since they typically rely on linguistic features. Text data constitute the dominant source of features for the majority of such models, although there is evidence from cognitive science that cues from other modalities contribute to the acquisition and representation of semantic knowledge. In this work, we propose the crossmodal extension of a two-tier text-based model, where semantic representations are encoded in the first layer, while the second layer is used for computing similarity between words. We exploit text- and image-derived features for performing computations at each layer, as well as various approaches for their crossmodal fusion. It is shown that the crossmodal model performs better (from 0.68 to 0.71 correlation coefficient) than the unimodal one for the task of similarity computation between words.
Anthology ID:
L16-1627
Volume:
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Month:
May
Year:
2016
Address:
Portorož, Slovenia
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
3973–3979
Language:
URL:
https://aclanthology.org/L16-1627
DOI:
Bibkey:
Cite (ACL):
Elias Iosif and Alexandros Potamianos. 2016. Crossmodal Network-Based Distributional Semantic Models. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3973–3979, Portorož, Slovenia. European Language Resources Association (ELRA).
Cite (Informal):
Crossmodal Network-Based Distributional Semantic Models (Iosif & Potamianos, LREC 2016)
Copy Citation:
PDF:
https://aclanthology.org/L16-1627.pdf