Noetic end-to-end response selection with supervised neural network based classifiers and unsupervised similarity models. (July 2020)

• Record Type: Journal Article
• Authors: Skórzewski, Paweł; Sieińska, Weronika; Kubis, Marek
• Is Part Of: Computer speech & language. Volume 62(2020)
• Publication Date: 2020-07
• Subjects: DSTC7 -- Dialogue systems -- Sentence selection -- Neural networks -- Unsupervised similarity models -- Ensemble models,; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101074
• Languages: English
• ISSNs: 0885-2308

Abstract

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.