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

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.
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02304597
Contributor : Antoine Caubrière <>
Submitted on : Thursday, October 3, 2019 - 1:22:27 PM
Last modification on : Wednesday, October 9, 2019 - 1:29:19 AM

File

Curriculum_based_transfer_lear...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02304597, version 1

Citation

Antoine Caubrière, Natalia Tomashenko, Antoine Laurent, Emmanuel Morin, Nathalie Camelin, et al.. Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability. Interspeech 2019, Sep 2019, Graz, Austria. ⟨hal-02304597⟩

Share

Metrics

Record views

7

Files downloads

11