From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding

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

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to reuse existing data in high-resource languages to develop models for low-resource scenarios. We introduce XSID, a new benchmark for cross-lingual (X) Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect.
To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer. We study two setups which differ by type and language coverage of the pre-trained embeddings. Our results show that jointly learning the main
tasks with masked language modeling is effective for slots, while machine translation works best for intent classification.
OriginalsprogEngelsk
TitelProceedings of NAACL
ForlagAssociation for Computational Linguistics
Publikationsdato2021
StatusUdgivet - 2021

Fingeraftryk

Dyk ned i forskningsemnerne om 'From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding'. Sammen danner de et unikt fingeraftryk.

Citationsformater