An Ensemble Model with Ranking for Social Dialogue

Ioannis Papaioannou, Amanda Cercas Curry, Jose Part, Igor Shalyminov, Xu Xinnuo, Yanchao Yu, Ondrej Dusek, Verena Rieser, Oliver Lemon

Research output: Contribution to conferencePaper

Abstract

Open-domain social dialogue is one of the long-standing goals of Artificial Intelligence. This year, the Amazon Alexa Prize challenge was announced for the first time, where real customers get to rate systems developed by leading universities worldwide. The aim of the challenge is to converse “coherently and engagingly with humans on popular topics for 20 minutes”. We describe our Alexa Prize system (called ‘Alana’) consisting of an ensemble of bots, combining rule-based and machine learning systems, and using a contextual ranking mechanism to choose a system response. The ranker was trained on real user feedback received during the competition, where we address the problem of how to train on the noisy and sparse feedback obtained during the competition.
Original languageEnglish
Publication statusPublished - 2017
EventNIPS 2017 Conversational AI Workshop - Long Beach Convention Center, Long Beach, United States
Duration: 8 Dec 20178 Dec 2017

Workshop

WorkshopNIPS 2017 Conversational AI Workshop
CountryUnited States
CityLong Beach
Period8/12/178/12/17

Fingerprint Dive into the research topics of 'An Ensemble Model with Ranking for Social Dialogue'. Together they form a unique fingerprint.

Cite this