Zero-Shot Learning for Semantic Utterance Classification
This addresses the challenge of classifying utterances into semantic categories without training data, which is useful for natural language processing applications, but it is incremental as it builds on existing zero-shot learning frameworks.
The paper tackles the problem of semantic utterance classification without any labeled examples for the target categories, proposing a zero-shot learning method that learns a semantic space from search engine query logs. It achieves state-of-the-art results on the SUC dataset by combining these semantic features with a supervised approach.
We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier $f: X \to Y$ 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 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.