Open Intent Discovery through Unsupervised Semantic Clustering and Dependency Parsing
This addresses the challenge of reducing manual effort in designing intents for new domains in dialog systems, though it is incremental as it builds on existing unsupervised and parsing techniques.
The paper tackles the problem of automatically discovering intents from unlabeled utterances in dialog systems, presenting an unsupervised two-stage approach that uses semantic clustering and dependency parsing to generate meaningful intent labels, achieving high precision and recall.
Intent understanding plays an important role in dialog systems, and is typically formulated as a supervised learning problem. However, it is challenging and time-consuming to design the intents for a new domain from scratch, which usually requires a lot of manual effort of domain experts. This paper presents an unsupervised two-stage approach to discover intents and generate meaningful intent labels automatically from a collection of unlabeled utterances in a domain. In the first stage, we aim to generate a set of semantically coherent clusters where the utterances within each cluster convey the same intent. We obtain the utterance representation from various pre-trained sentence embeddings and present a metric of balanced score to determine the optimal number of clusters in K-means clustering for balanced datasets. In the second stage, the objective is to generate an intent label automatically for each cluster. We extract the ACTION-OBJECT pair from each utterance using a dependency parser and take the most frequent pair within each cluster, e.g., book-restaurant, as the generated intent label. We empirically show that the proposed unsupervised approach can generate meaningful intent labels automatically and achieve high precision and recall in utterance clustering and intent discovery.