@article{McCrae2011, 
author = {Patrick McCrae and Wolfgang Menzel and Maosong SUN},
title = {A Computational Model of Concept Generalization in Cross-Modal Reference},
year = {2011},
journal = {Tsinghua Science and Technology},
volume = {16},
number = {2},
pages = {113-120},
keywords = {vision-language interaction, cross-modal reference, syntactic disambiguation},
url = {https://www.sciopen.com/article/10.1016/S1007-0214(11)70018-9},
doi = {10.1016/S1007-0214(11)70018-9},
abstract = {Cross-modal interactions between visual understanding and linguistic processing substantially contribute to the remarkable robustness of human language processing. We argue that the formation of cross-modal referential links is a prerequisite for the occurrence of cross-modal interactions between vision and language. In this paper we examine a computational model for a cross-modal reference formation with respect to its robustness against conceptual underspecification in the visual modality. This investigation is motivated by the fact that natural systems are well capable of establishing a cross-modal reference between modalities with different degrees of conceptual specification. In the investigated model, conceptually under-specified context information continues to drive the syntactic disambiguation of verb-centered syntactic ambiguities as long as the visual context contains the situation arity information of the visual scene.}
}