Typically, spoken language understanding (SLU) models are trained on annotated data which are costly to gather. Aiming to reduce data needs for bootstrapping a SLU system for a new language, we present a simple but effective weight transfer approach using data from another language. The approach is evaluated with our promising multi-task SLU framework developed towards different languages. We evaluate our approach on the ATIS and a real-world SLU dataset, showing that i) our monolingual models outperform the state-of-the-art, ii) we can reduce data amounts needed for bootstrapping a SLU system for a new language greatly, and iii) while multitask training improves over separate training, different weight transfer settings may work best for different SLU modules.
@article{arxiv.1904.01825,
title = {Cross-lingual transfer learning for spoken language understanding},
author = {Quynh Ngoc Thi Do and Judith Gaspers},
journal= {arXiv preprint arXiv:1904.01825},
year = {2019}
}