Cross-Lingual knowledge transfer for NLU (Slot Filling)/NER

Cross-Lingual knowledge transfer for NLU (Slot Filling)/NER

Research questions

  • Which cross-lingual knowledge transfer strategy is the most beneficial for the Slot Filing task in the given domain (emergency calls)? Pros/cons of different approaches. 
  • Which strategy to filter translated training data seem to be the most advantageous?  
  • How do cross-lingual knowledge transfer strategies in question and their effects differ for different model architectures? 

Data: simulated emergency dialogues in German and English from the NotAs project, publicly available datasets for NER/Slot Filling tasks (e.g. SGD, MultiWOZ etc.) 

Paper suggestions and useful links

  • Gaspers, J., Karanasou, P., & Chatterjee, R. (2018). Selecting machine-translated data for quick bootstrapping of a natural language understanding system. arXiv preprint arXiv:1805.09119. Link: