Zero-Shot Learning for Semantic Utterance Classification [article]

Yann N. Dauphin, Gokhan Tur, Dilek Hakkani-Tur, Larry Heck
2014 arXiv   pre-print
We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier f: X → Y for problems where none of the semantic categories Y are present in the training set. The framework uncovers the link between categories and utterances using a semantic space. We show that this semantic space can be learned by deep neural networks trained on large amounts of search engine query log data. More precisely, we propose a novel method that can learn discriminative
more » ... semantic features without supervision. It uses the zero-shot learning framework to guide the learning of the semantic features. We demonstrate the effectiveness of the zero-shot semantic learning algorithm on the SUC dataset collected by (Tur, 2012). Furthermore, we achieve state-of-the-art results by combining the semantic features with a supervised method.
arXiv:1401.0509v3 fatcat:bcri3qreyfdqtm3npsmfat77m4