SIMVECS: Similarity-based vectors for utterance representation in conversational AI systems

Abstract

Conversational AI systems are gaining a lot of attention recently in both industrial and scientific domains, providing a natural way of interaction between customers and adaptive intelligent systems. A key requirement in these systems is the ability to efficiently parse user queries, understand the intent behind each query, and provide adequate responses to users. Therefore, many applications such as conversation bots and smart IoT devices has a natural language understanding (LU) service integrated within. One of the greatest challenges of language understanding services is efficient utterance (sentence) representation in vector space, which is an essential step for most ML tasks. In this paper, we propose a novel approach for generating vector space representations of conversational utterances using pair-wise similarity metrics. The proposed approach uses only a few corpora to tune the weights of the similarity metric without relying on external general purpose ontologies. Our experiments confirm that the generated vectors can improve the performance of LU services in unsupervised, semi-supervised and supervised learning tasks over state-of-the-art prior works.