Unsupervised Alignment for Segmental-based Language Understanding

Stéphane Huet, Fabrice Lefèvre

Abstract: Recent years' most efficient approaches for language understanding are statistical. These approaches benefit from a segmental semantic annotation of corpora. To reduce the production cost of such corpora, this paper proposes a method that is able to match first identified concepts with word sequences in an unsupervised way. This method based on automatic alignment is used by an understanding system based on conditional random fields and is evaluated on a spoken dialogue task using either manual or automatic transcripts.