Dealing with uncertain input in word learning

Versteegh, Maarten; Ten Bosch, Louis; Boves, Lou

doi:10.1109/DEVLRN.2010.5578866

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

会議論文

Dealing with uncertain input in word learning

MPS-Authors

/persons/resource/persons41922

Versteegh, Maarten
Centre for Language Studies • Radboud University Nijmegen;
International Max Planck Research School for Language Sciences, MPI for Psycholinguistics, Max Planck Society;

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

Versteegh_2010_9th_IEEE_Conference_Development_Learning.pdf
(出版社版), 844KB

付随資料 (公開)

There is no public supplementary material available

引用

Versteegh, M., Ten Bosch, L., & Boves, L. (2010). Dealing with uncertain input in word learning. In Proceedings of the IXth IEEE International Conference on Development and Learning (ICDL). Ann Arbor, MI, 18-21 Aug. 2010 (pp. 46-51). IEEE.

引用: https://hdl.handle.net/11858/00-001M-0000-000F-8294-A

要旨

In this paper we investigate a computational model of word learning, that is embedded in a cognitively and ecologically plausible framework. Multi-modal stimuli from four different speakers form a varied source of experience. The model incorporates active learning, attention to a communicative setting and clarity of the visual scene. The model's ability to learn associations between speech utterances and visual concepts is evaluated during training to investigate the influence of active learning under conditions of uncertain input. The results show the importance of shared attention in word learning and the model's robustness against noise.