NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Variational inference for adaptor grammars
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Modeling perspective using adaptor grammars
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Reducing grounded learning tasks to grammatical inference
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Hi-index | 0.00 |
This paper uses an unsupervised model of grounded language acquisition to study the role that social cues play in language acquisition. The input to the model consists of (orthographically transcribed) child-directed utterances accompanied by the set of objects present in the non-linguistic context. Each object is annotated by social cues, indicating e.g., whether the caregiver is looking at or touching the object. We show how to model the task of inferring which objects are being talked about (and which words refer to which objects) as standard grammatical inference, and describe PCFG-based unigram models and adaptor grammar-based collocation models for the task. Exploiting social cues improves the performance of all models. Our models learn the relative importance of each social cue jointly with word-object mappings and collocation structure, consistent with the idea that children could discover the importance of particular social information sources during word learning.