Skip to Main content Skip to Navigation
Conference papers

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

Abstract : During the last couple of years, Recurrent Neural Networks (RNN) have reached state-of-the-art performances on most of the sequence modelling problems. In particular, the sequence to sequence model and the neural CRF have proved to be very effective in this domain. In this article, we propose a new RNN architecture for sequence labelling, leveraging gated recurrent layers to take arbitrarily long contexts into account, and using two decoders operating forward and backward. We compare several variants of the proposed solution and their performances to the state-of-the-art. Most of our results are better than the state-of-the-art or very close to it and thanks to the use of recent technologies, our architecture can scale on corpora larger than those used in this work.
Complete list of metadatas

Cited literature [61 references]  Display  Hide  Download

https://hal.inria.fr/hal-02085093
Contributor : Loïc Grobol <>
Submitted on : Saturday, March 30, 2019 - 11:25:23 AM
Last modification on : Friday, January 24, 2020 - 3:02:09 PM

File

main.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - ShareAlike 4.0 International License

Identifiers

  • HAL Id : hal-02085093, version 1

Collections

Citation

Marco Dinarelli, Loïc Grobol. Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling. CICLing 2019 - 20th International Conference on Computational Linguistics and Intelligent Text Processing, Apr 2019, La Rochelle, France. ⟨hal-02085093⟩

Share

Metrics

Record views

112

Files downloads

259