Cross-lingual Multi-task Transfer for Zero-shot Task-oriented Dialog

Rob van der Goot, Marija Stepanovic, Alan Ramponi, Ibrahim Sharaf, Ahmet Üstün, Aizhan Imankulova, Siti Oryza Khairunnisa, Mamoru Komachi, Barbara Plank

Research output: Contribution to conference - NOT published in proceeding or journalConference abstract for conferenceResearchpeer-review


Digital assistants are becoming an integral part of everyday life. However, commercial digital assistants are only available for a limited set of languages. Because of this, a vast amount of people can not use these devices in their native tongue.
In this work, we focus on two core tasks within the digital assistant pipeline: intent classification and slot detection. Intent classification recovers the goal of the utterance, whereas slot detection identifies important properties regarding this goal. Besides introducing a novel cross-lingual dataset for these tasks, consisting of 11 languages, we evaluate a variety of models: 1)
multilingually pretrained transformer-based models, 2) we supplement these models with auxiliary tasks to evaluate whether multi-task learning can be beneficial, and 3) annotation transfer with neural machine translation.
Original languageEnglish
Publication date25 Sept 2021
Publication statusPublished - 25 Sept 2021
: RESOURCEs and representations For Under-resourced Languages and domains
- Gothenburg, Gothenburg, Sweden
Duration: 25 Nov 2020 → …


Period25/11/2020 → …
Internet address


Dive into the research topics of 'Cross-lingual Multi-task Transfer for Zero-shot Task-oriented Dialog'. Together they form a unique fingerprint.

Cite this