Semantic Ambiguity Detection in Sentence Classifcation using Task-Specifc Embeddings

Abstract

Ambiguity is a major obstacle to providing services based on sentence classifcation. However, because of the structural limitations of the service, there may not be suffcient contextual information to resolve the ambiguity. In this situation, we focus on ambiguity detection so that service design considering ambiguity is possible. We utilize similarity in a semantic space to detect ambiguity in service scenarios1 and training data. In addition, we apply task-specifc embedding to improve performance. Our results demonstrate that ambiguities and resulting labeling errors in training data or scenarios can be detected. Additionally, we con-frm that it can be used to debug services.