Finding Dominant User Utterances And System Responses in Conversations
This work addresses the labor-intensive task of dialog design for rule-based frameworks, offering an incremental improvement in automating intent-response pairing.
The paper tackles the problem of automatically identifying frequent user intents and corresponding agent responses from prior conversations to reduce manual effort in dialog design, achieving up to 10% absolute improvement in F1-scores compared to standard K-means clustering.
There are several dialog frameworks which allow manual specification of intents and rule based dialog flow. The rule based framework provides good control to dialog designers at the expense of being more time consuming and laborious. The job of a dialog designer can be reduced if we could identify pairs of user intents and corresponding responses automatically from prior conversations between users and agents. In this paper we propose an approach to find these frequent user utterances (which serve as examples for intents) and corresponding agent responses. We propose a novel SimCluster algorithm that extends standard K-means algorithm to simultaneously cluster user utterances and agent utterances by taking their adjacency information into account. The method also aligns these clusters to provide pairs of intents and response groups. We compare our results with those produced by using simple Kmeans clustering on a real dataset and observe upto 10% absolute improvement in F1-scores. Through our experiments on synthetic dataset, we show that our algorithm gains more advantage over K-means algorithm when the data has large variance.