Code-Mixed Intermediate Fine-Tuning for Multilingual Dialogue State Tracking Performance

Recent progress in task-oriented neural dialogue systems is largely focused on a handful of languages, as annotation of training data is tedious and expensive. Machine translation has been used to make systems multilingual, but this can introduce a pipeline of errors. Another promising solution is using cross-lingual transfer learning through pretrained multilingual models. Existing methods train multilingual models with additional codemixed task data or refine the cross-lingual representations through parallel ontologies. In this work, we enhance the transfer learning process by intermediate

Research goal: What is the effect of intermediate fine-tuning with code-mixed data on the inference latency and throughput of multilingual dialogue state tracking models evaluated on XTREME-R?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.