Leveraging Cross-Lingual Transfer Learning in Spoken Named Entity Recognition Systems
This addresses the problem of low-resource spoken NER for languages like Dutch, but it is incremental as it builds on existing transfer learning methods.
The paper tackled spoken Named Entity Recognition (NER) for spoken document retrieval by applying cross-lingual transfer learning across Dutch, English, and German, finding that an End-to-End model outperformed a pipeline model and transfer from German to Dutch improved performance by 7% over the standalone Dutch system.
Recent Named Entity Recognition (NER) advancements have significantly enhanced text classification capabilities. This paper focuses on spoken NER, aimed explicitly at spoken document retrieval, an area not widely studied due to the lack of comprehensive datasets for spoken contexts. Additionally, the potential for cross-lingual transfer learning in low-resource situations deserves further investigation. In our study, we applied transfer learning techniques across Dutch, English, and German using both pipeline and End-to-End (E2E) approaches. We employed Wav2Vec2 XLS-R models on custom pseudo-annotated datasets to evaluate the adaptability of cross-lingual systems. Our exploration of different architectural configurations assessed the robustness of these systems in spoken NER. Results showed that the E2E model was superior to the pipeline model, particularly with limited annotation resources. Furthermore, transfer learning from German to Dutch improved performance by 7% over the standalone Dutch E2E system and 4% over the Dutch pipeline model. Our findings highlight the effectiveness of cross-lingual transfer in spoken NER and emphasize the need for additional data collection to improve these systems.