Chat or Learn: a Data-Driven Robust Question-Answering System

Gabriel Luthier, Andrei Popescu-Belis

Abstract
We present a voice-based conversational agent which combines the robustness of chatbots and the utility of question answering (QA) systems. Indeed, while data-driven chatbots are typically user-friendly but not goal-oriented, QA systems tend to perform poorly at chitchat. The proposed chatbot relies on a controller which performs dialogue act classification and feeds user input either to a sequence-to-sequence chatbot or to a QA system. The resulting chatbot is a spoken QA application for the Google Home smart speaker. The system is endowed with general-domain knowledge from Wikipedia articles and uses coreference resolution to detect relatedness between questions. We present our choices of data sets for training and testing the components, and present the experimental results that helped us optimize the parameters of the chatbot. In particular, we discuss the appropriateness of using the SQuAD dataset for evaluating end-to-end QA, in the light of our system’s behavior.
Anthology ID:
2020.lrec-1.672
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
5474–5480
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.672
DOI:
Bibkey:
Cite (ACL):
Gabriel Luthier and Andrei Popescu-Belis. 2020. Chat or Learn: a Data-Driven Robust Question-Answering System. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5474–5480, Marseille, France. European Language Resources Association.
Cite (Informal):
Chat or Learn: a Data-Driven Robust Question-Answering System (Luthier & Popescu-Belis, LREC 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2020.lrec-1.672.pdf
PDF Search