Marco Dinarelli con la sua prima pubblicazione in una rivista IEEE Marco Dinarelli
Web site of Marco Dinarelli in English  Site web de Marco Dinarelli en français  Sito web di Marco Dinarelli in italiano 


LIG (UMR 5217)
Office 327
700 avenue Centrale
Campus de Saint-Martin-d’Hères, France


Email:
marco [dot] dinarelli [at] univ-grenoble-alpes [dot] fr
marco [dot] dinarelli [at] gmail [dot] com

                        Curriculum Vitae           Profilo di Marco Dinarelli su LinkedIn


Attualità recenti

03 / 04 / 2020:
Articolo accettato alla conferenza francese TALN 2020 (Traitement Automaque des Langues Naturelles)

13 / 02 / 2020:
Articolo accettato alla conferenza LREC 2020 (Language Resources and Evaluation Conference)

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

Indice degli argomenti:

Description

Seq2Biseq tool is the software used for the paper Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling. It replaces, extends and improves the previous tool LD-RNN, used for the paper Label-Dependencies Aware Recurrent Neural Networks.
Seq2Biseq is coded in pytorch and it follows the same research trend as our previous papers, where a bidirectional output-side context is used for current decision. A schema of the high-level architecture is shown in the following image.
Seq2Biseq model architecture


The idea is similar to those used in Deliberation Networks, and Asynchronous bidirectional networks for Machine Translation.

Features

  • Bidirectional backward-forward decoding

Download

Please send me an email @univ-grenoble-alpes for now.

I'm going to git the tool.

Licence

Seq2Biseq is provided under Creative-Commons BY-SA licence

Installation and usage

See the README file in the package.