Multimodal Semantic Learning from Child-Directed Input

Angeliki Lazaridou; Grzegorz Chrupala; Raquel Fernández; Marco Baroni

Multimodal Semantic Learning from Child-Directed Input

Angeliki Lazaridou, Grzegorz Chrupala, Raquel Fernández, Marco Baroni

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

Children learn the meaning of words by being exposed to perceptually rich situations (linguistic discourse, visual scenes, etc). Current computational learning models typically simulate these rich situations through impoverished symbolic approximations. In this work, we present a distributed word learning model that operates on child-directed speech paired with realistic visual scenes. The model integrates linguistic and extra-linguistic information (visual and social cues), handles referential uncertainty, and correctly learns to associate words with objects, even in cases of limited linguistic exposure.

Original language	English
Title of host publication	Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Publisher	Association for Computational Linguistics
Pages	387-392
ISBN (Electronic)	9781941643914
Publication status	Published - Jun 2016
Event	North American Chapter of the Association for Computational Linguistics: Human Language Technologies - San Diego, United States Duration: 12 Jun 2016 → 17 Jun 2016 Conference number: 15 http://naacl.org/naacl-hlt-2016/index.html

Conference

Conference	North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Abbreviated title	NAACL HLT 2016
Country/Territory	United States
City	San Diego
Period	12/06/16 → 17/06/16
Internet address	http://naacl.org/naacl-hlt-2016/index.html

Access to Document

Cite this

Lazaridou, A., Chrupala, G., Fernández, R., & Baroni, M. (2016). Multimodal Semantic Learning from Child-Directed Input. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 387-392). Association for Computational Linguistics. http://clic.cimec.unitn.it/marco/publications/lazaridou-etal-multimodal-learning-from-cdi-naacl2016.pdf

@inproceedings{8091b5de7a8e43698a4ae6f3317083d9,

title = "Multimodal Semantic Learning from Child-Directed Input",

abstract = "Children learn the meaning of words by being exposed to perceptually rich situations (linguistic discourse, visual scenes, etc). Current computational learning models typically simulate these rich situations through impoverished symbolic approximations. In this work, we present a distributed word learning model that operates on child-directed speech paired with realistic visual scenes. The model integrates linguistic and extra-linguistic information (visual and social cues), handles referential uncertainty, and correctly learns to associate words with objects, even in cases of limited linguistic exposure.",

author = "Angeliki Lazaridou and Grzegorz Chrupala and Raquel Fern{\'a}ndez and Marco Baroni",

year = "2016",

month = jun,

language = "English",

pages = "387--392",

booktitle = "Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",

publisher = "Association for Computational Linguistics",

note = "North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 ; Conference date: 12-06-2016 Through 17-06-2016",

url = "http://naacl.org/naacl-hlt-2016/index.html",

}

Lazaridou, A, Chrupala, G, Fernández, R & Baroni, M 2016, Multimodal Semantic Learning from Child-Directed Input. in Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, pp. 387-392, North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, United States, 12/06/16. <http://clic.cimec.unitn.it/marco/publications/lazaridou-etal-multimodal-learning-from-cdi-naacl2016.pdf>

Multimodal Semantic Learning from Child-Directed Input. / Lazaridou, Angeliki; Chrupala, Grzegorz; Fernández, Raquel et al.
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 2016. p. 387-392.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Multimodal Semantic Learning from Child-Directed Input

AU - Lazaridou, Angeliki

AU - Chrupala, Grzegorz

AU - Fernández, Raquel

AU - Baroni, Marco

N1 - Conference code: 15

PY - 2016/6

Y1 - 2016/6

N2 - Children learn the meaning of words by being exposed to perceptually rich situations (linguistic discourse, visual scenes, etc). Current computational learning models typically simulate these rich situations through impoverished symbolic approximations. In this work, we present a distributed word learning model that operates on child-directed speech paired with realistic visual scenes. The model integrates linguistic and extra-linguistic information (visual and social cues), handles referential uncertainty, and correctly learns to associate words with objects, even in cases of limited linguistic exposure.

AB - Children learn the meaning of words by being exposed to perceptually rich situations (linguistic discourse, visual scenes, etc). Current computational learning models typically simulate these rich situations through impoverished symbolic approximations. In this work, we present a distributed word learning model that operates on child-directed speech paired with realistic visual scenes. The model integrates linguistic and extra-linguistic information (visual and social cues), handles referential uncertainty, and correctly learns to associate words with objects, even in cases of limited linguistic exposure.

M3 - Conference contribution

SP - 387

EP - 392

BT - Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

PB - Association for Computational Linguistics

T2 - North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Y2 - 12 June 2016 through 17 June 2016

ER -

Multimodal Semantic Learning from Child-Directed Input

Abstract

Conference

Access to Document

Fingerprint

Cite this