Cross-lingual transfer learning for spoken language understanding
This work addresses the costly data annotation problem for SLU systems in new languages, but it appears incremental as it builds on existing multi-task frameworks and transfer learning concepts.
The paper tackles the problem of reducing annotated data needs for bootstrapping spoken language understanding (SLU) systems in new languages by proposing a weight transfer approach using data from another language, showing that it outperforms state-of-the-art monolingual models and greatly reduces data requirements.
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.