Classification-based Contextual Preferences
Shachar Mirkin, Ido Dagan, Lili Kotlerman, Idan Szpektor · 2011
This paper addresses context matching in tex-tual inference. We formulate the task under the Contextual Preferences framework which broadly captures contextual aspects of infer-ence. We propose a generic classification-based scheme under this framework which co-herently attends to context matching in infer-ence and may be employed in any inference-based task. As a test bed for our scheme we use the Name-based Text Categorization (TC) task. We define an integration of Contextual Prefer-ences into the TC setting and present a concrete self-supervised model which instantiates the generic scheme and is applied to address con-text matching in the TC task. Experiments on standard TC datasets show that our approach outperforms the state of the art in context mod-eling for Name-based TC. 1