On Spoken Language Understanding Systems for Low Resourced Languages

Anonymous

Abstract: Spoken dialog systems are slowly becoming and integral part of the human experience due to their various advantages over textual interfaces. Spoken language understanding (SLU) systems are fundamental building blocks of spoken dialog systems. But creating SLU systems for low resourced languages is still a challenge. In a large number of low resourced settings we don't have access to enough data to build automatic speech recognition (ASR) technologies, which are fundamental to any SLU system. Also, ASR based SLU systems do not generalize to unwritten languages. In this paper, we present a series of experiments to explore an extremely low resourced setting - something we refer to as a true k-shot setting, where we perform intent classification with systems trained on different values of k. We test our system on English and Flemish and find that even in such granular settings and no language specific ASR technology, we can create SLU systems that can be deployed in the real world.