Quantized-Dialog Language Model for Goal-Oriented Conversational Systems
This addresses the challenge of accurate utterance selection in automated conversational systems like restaurant reservations, representing an incremental improvement over existing methods.
The paper tackles the problem of selecting the correct next utterance in goal-oriented dialog systems by quantizing the dialog space into clusters and using an n-gram language model across them, achieving high accuracy and outperforming neural network-based state-of-the-art approaches on the DSTC6 benchmark.
We propose a novel methodology to address dialog learning in the context of goal-oriented conversational systems. The key idea is to quantize the dialog space into clusters and create a language model across the clusters, thus allowing for an accurate choice of the next utterance in the conversation. The language model relies on n-grams associated with clusters of utterances. This quantized-dialog language model methodology has been applied to the end-to-end goal-oriented track of the latest Dialog System Technology Challenges (DSTC6). The objective is to find the correct system utterance from a pool of candidates in order to complete a dialog between a user and an automated restaurant-reservation system. Our results show that the technique proposed in this paper achieves high accuracy regarding selection of the correct candidate utterance, and outperforms other state-of-the-art approaches based on neural networks.