A Hybrid Solution to Learn Turn-Taking in Multi-Party Service-based Chat Groups
This work addresses turn-taking prediction for service-based chat groups, but it is incremental as it combines existing methods on a new synthetic dataset.
The paper tackled the problem of predicting the next participant in multi-party chat groups by integrating turn-taking classifiers based on MLE, CNN, and FSA, achieving an accuracy of 95.65% with the hybrid approach compared to 92.34% for CNN alone.
To predict the next most likely participant to interact in a multi-party conversation is a difficult problem. In a text-based chat group, the only information available is the sender, the content of the text and the dialogue history. In this paper we present our study on how these information can be used on the prediction task through a corpus and architecture that integrates turn-taking classifiers based on Maximum Likelihood Expectation (MLE), Convolutional Neural Networks (CNN) and Finite State Automata (FSA). The corpus is a synthetic adaptation of the Multi-Domain Wizard-of-Oz dataset (MultiWOZ) to a multiple travel service-based bots scenario with dialogue errors and was created to simulate user's interaction and evaluate the architecture. We present experimental results which show that the CNN approach achieves better performance than the baseline with an accuracy of 92.34%, but the integrated solution with MLE, CNN and FSA achieves performance even better, with 95.65%.