Logo image
From Cambridge to Pisa: A Journey into Cross-Lingual Dialogue Domain Adaptation for Conversational Agents
Conference proceeding   Open access   Peer reviewed

From Cambridge to Pisa: A Journey into Cross-Lingual Dialogue Domain Adaptation for Conversational Agents

Tiziano Labruna and B Magnini
CLiC-it 2021 Italian Conference on Computational Linguistics 2021: Proceedings of the Eighth Italian Conference on Computational Linguistics Milan, Italy, June 29 - July 1, 2022, Vol.3033, pp.193-199
CEUR Workshop Proceedings, 3033
CLiC-it 2021 (Milan, 29/06/2022–01/07/2022)
2021
Handle:
https://hdl.handle.net/10863/51505

Abstract

Speech processing Computational Linguistics
Domain and language shift are still major bottlenecks for a vast range of task-oriented dialogue systems. This paper focuses on data-driven models for dialogue state tracking, and builds on top of recent work on dialogue domain adaptation, showing that state-of-the-art models are very sensible to language shift obtained through automatic translation. Experiments show that combining training data for the two languages (English and Italian) is always beneficial, while combining domains does not increase performance. As a relevant side effect of our work, we present a new dataset for dialogue state tracking available for Italian, derived from MultiWOZ 2.3.
pdf
2021.clicit-1.31522.04 kBDownloadView
Open Access
url
https://ceur-ws.org/Vol-3033/paper71.pdfView

Details

Metrics

1 Record Views
Logo image