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 - Laboratoire LIG

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

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

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

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

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

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

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

Effective Spoken Language Labeling with Deep Recurrent Neural Networks


Jun 20, 2017
Marco Dinarelli, Yoann Dupont, Isabelle Tellier

* 8 pages. Rejected from IJCAI 2017, good remarks overall, but slightly off-topic as from global meta-reviews. Recommendations: 8, 6, 6, 4. arXiv admin note: text overlap with arXiv:1706.01740 

  Access Paper or Ask Questions

Label-Dependencies Aware Recurrent Neural Networks


Jun 06, 2017
Yoann Dupont, Marco Dinarelli, Isabelle Tellier

* 22 pages, 3 figures. Accepted at CICling 2017 conference. Best Verifiability, Reproducibility, and Working Description award 

  Access Paper or Ask Questions

Improving Recurrent Neural Networks For Sequence Labelling


Jun 08, 2016
Marco Dinarelli, Isabelle Tellier

* 21 pages, 4 figures 

  Access Paper or Ask Questions