Services on Demand
Journal
Article
Indicators
Cited by SciELO
Access statistics
Related links
Similars in SciELO
Share
Computación y Sistemas
On-line version ISSN 2007-9737Print version ISSN 1405-5546
Abstract
BOUSSAHA, Basma El Amel; HERNANDEZ, Nicolas; JACQUIN, Christine and MORIN, Emmanuel. Towards Simple but Efficient Next Utterance Ranking. Comp. y Sist. [online]. 2019, vol.23, n.3, pp.1055-1064. Epub Aug 09, 2021. ISSN 2007-9737. https://doi.org/10.13053/cys-23-3-3272.
Retrieval-based dialogue systems converse with humans by ranking candidate responses according to their relevance to the history of the conversation (context). Recent studies either match the context with the response on only sequence level or use complex architectures to match them on the word and sequence levels. We show that both information levels are important and that a simple architecture can capture them effectively. We propose an end-to-end multi-level response retrieval dialogue system. Our model learns to match the context with the best response by computing their semantic similarity on the word and sequence levels. Empirical evaluation on two dialogue datasets shows that our model outperforms several state-of-the-art systems and performs as good as the best system while being conceptually simpler.
Keywords : Dialogue systems; response retrieval; sequence similarity.
![](/img/en/iconPDFDocument.gif)