EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification
Georgios P. Spithourakis, Ivan Vulić, Michał Lis, Iñigo Casanueva, Paweł Budzianowski
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/PolyAI-LDN/evi-paperOfficialnone★ 5
Abstract
Knowledge-based authentication is crucial for task-oriented spoken dialogue systems that offer personalised and privacy-focused services. Such systems should be able to enrol (E), verify (V), and identify (I) new and recurring users based on their personal information, e.g. postcode, name, and date of birth. In this work, we formalise the three authentication tasks and their evaluation protocols, and we present EVI, a challenging spoken multilingual dataset with 5,506 dialogues in English, Polish, and French. Our proposed models set the first competitive benchmarks, explore the challenges of multilingual natural language processing of spoken dialogue, and set directions for future research.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| EVI en-GB | Fuzzy Retrieval | Top-1 (%) | 67.77 | — | Unverified |
| EVI fr-FR | Fuzzy Retrieval | Top-1 (%) | 80.83 | — | Unverified |
| EVI pl-PL | Fuzzy Retrieval | Top-1 (%) | 95.13 | — | Unverified |