Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Picture for Marco Dinarelli

Marco Dinarelli

Université Grenoble Alpes, Laboratoires: LIG - Getalp Group

TArC: Tunisian Arabish Corpus First complete release


Jul 11, 2022
Elisa Gugliotta, Marco Dinarelli

* In Proceedings of the Language Resources and Evaluation Conference (LREC2022), Marseille. European Language Resources Association (pp. 1125-1136) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Toward Low-Cost End-to-End Spoken Language Understanding


Jul 01, 2022
Marco Dinarelli, Marco Naguib, François Portet

* Accepted for publication at Interspeech 2022; Slightly improved (longer) version 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Vers la compréhension automatique de la parole bout-en-bout à moindre effort


Jul 01, 2022
Marco Naguib, François Portet, Marco Dinarelli

* Language: French; Paper accepted for publication at the French Conference TALN 2022; preliminary work for the Interspeech 2022 paper (coming soon) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech


Apr 23, 2021
Solene Evain, Ha Nguyen, Hang Le, Marcely Zanon Boito, Salima Mdhaffar, Sina Alisamir, Ziyi Tong, Natalia Tomashenko, Marco Dinarelli, Titouan Parcollet, Alexandre Allauzen, Yannick Esteve, Benjamin Lecouteux, Francois Portet, Solange Rossato, Fabien Ringeval, Didier Schwab, Laurent Besacier

* Submitted to Interspeech 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Divide and Rule: Training Context-Aware Multi-Encoder Translation Models with Little Resources


Mar 31, 2021
Lorenzo Lupo, Marco Dinarelli, Laurent Besacier


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Task Sequence Prediction For Tunisian Arabizi Multi-Level Annotation


Nov 10, 2020
Elisa Gugliotta, Marco Dinarelli, Olivier Kraif

* Paper accepted at the Fifth Arabic Natural Language Processing Workshop (WANLP) 2020 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

TArC: Incrementally and Semi-Automatically Collecting a Tunisian Arabish Corpus


Mar 24, 2020
Elisa Gugliotta, Marco Dinarelli

* Paper accepted at the Language Resources and Evaluation Conference (LREC) 2020 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Data Efficient End-To-End Spoken Language Understanding Architecture


Feb 14, 2020
Marco Dinarelli, Nikita Kapoor, Bassam Jabaian, Laurent Besacier

* Accepted to ICASSP 2020 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds


Sep 16, 2019
Marco Dinarelli, Loïc Grobol

* 12 pages + bibliography. English version, and slight improvement, of the paper published at the French conference TALN 2019 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling


Apr 16, 2019
Marco Dinarelli, Loïc Grobol

* Slightly improved version of the paper accepted to the CICling 2019 conference 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>