# Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability

## TL;DR

This paper introduces a curriculum-based transfer learning method for end-to-end spoken language understanding that effectively leverages out-of-domain data, achieving state-of-the-art results and demonstrating strong domain portability.

## Contribution

It proposes a novel curriculum learning-based transfer strategy for end-to-end SLU, improving performance and domain adaptability over traditional pipeline methods.

## Key findings

- Achieves best published results on French MEDIA and PORTMEDIA corpora
- Outperforms classical pipeline SLU approaches
- Demonstrates strong domain portability of the end-to-end model

## Abstract

We present an end-to-end approach to extract semantic concepts directly from the speech audio signal. To overcome the lack of data available for this spoken language understanding approach, we investigate the use of a transfer learning strategy based on the principles of curriculum learning. This approach allows us to exploit out-of-domain data that can help to prepare a fully neural architecture. Experiments are carried out on the French MEDIA and PORTMEDIA corpora and show that this end-to-end SLU approach reaches the best results ever published on this task. We compare our approach to a classical pipeline approach that uses ASR, POS tagging, lemmatizer, chunker... and other NLP tools that aim to enrich ASR outputs that feed an SLU text to concepts system. Last, we explore the promising capacity of our end-to-end SLU approach to address the problem of domain portability.