Open-domain Conversational Agent based on Pre-trained Transformers for Human-Robot Interaction

Mariana Fernandes, Plinio Moreno

2022

Abstract

Generative pre-trained transformers belong to the breakthroughs in Natural Language Processing (NLP), allowing Human-Robot Interactions (e.g. the creation of an open-domain chatbot). However, a substantial amount of research and available data are in English, causing low-resourced languages to be overlooked. This work addresses this problem for European Portuguese with two options: (i) Translation of the sentences before and after using the model fine-tuned on an English-based dataset, (ii) Translation of the English-based dataset to Portuguese and then fine-tune this model on it. We rely on the DialoGPT (dialogue generative pre-trained transformer), a tunable neural conversational answer generation model that learns the basic skills to conduct a dialogue. We use two sources of evaluation: (i) Metrics for text generation based on uncertainty (i.e. perplexity), and similarity between sentences (i.e. BLEU, METEOR and ROUGE) and (ii) Human-based evaluation of the sentences. The translation of sentences before and after of the modified DialoGPT model, using the Daily Dialogue dataset led to the best results.

Paper Citation

in Harvard Style

Fernandes M. and Moreno P. (2022). Open-domain Conversational Agent based on Pre-trained Transformers for Human-Robot Interaction. In Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA, ISBN 978-989-758-584-5, pages 168-175. DOI: 10.5220/0011300800003277

in Bibtex Style

@conference{delta22,
author={Mariana Fernandes and Plinio Moreno},
title={Open-domain Conversational Agent based on Pre-trained Transformers for Human-Robot Interaction},
booktitle={Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,},
year={2022},
pages={168-175},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011300800003277},
isbn={978-989-758-584-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,
TI - Open-domain Conversational Agent based on Pre-trained Transformers for Human-Robot Interaction
SN - 978-989-758-584-5
AU - Fernandes M.
AU - Moreno P.
PY - 2022
SP - 168
EP - 175
DO - 10.5220/0011300800003277