Noetic end-to-end response selection with supervised neural network based classifiers and unsupervised similarity models

Highlights

• Ensemble models are good and simple solutions for dialog system response selection.

• Ensemble of neural classifiers and similarity models good for sentence selection.

• Unsupervised similarity models can be used as baselines in dialog system challenges.

Abstract

This paper describes a solution for the Noetic End-to-End Response Selection challenge – one of the tasks of the 7th Dialog System Technology Challenge. The goal of the task is to select the most appropriate continuation of a dialogue from a given set of responses. We approach this problem by building an ensemble of supervised neural network based classifiers and unsupervised similarity models. The dialogue continuation is selected according to a score that aggregates the rankings of candidate responses determined by the models in the ensemble.