papers AI Learner
The Github is limit! Click to go to the new site.

Cross-lingual transfer learning for spoken language understanding

2019-04-03
Quynh Ngoc Thi Do, Judith Gaspers

Abstract

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1904.01825

PDF

https://arxiv.org/pdf/1904.01825


Comments

Content