Automatic Detection and Classification of Argument Components using Multi-task Deep Neural Network

Abstract : In this article we propose a novel method for automatically extracting and classifying argument components from raw texts. We introduce a multi-task deep learning framework exploiting weight parameters trained on auxiliary simple tasks, such as Part-Of-Speech tagging or chunking, in order to solve more complex tasks that require a fine-grained understanding of natural language. Interestingly, our results show that the use of advanced deep learning techniques framed in a multi-task setting enables competing with state-of-the-art systems that depend on handcrafted features.
Document type :
Conference papers
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02292945
Contributor : Sébastien Harispe <>
Submitted on : Monday, September 23, 2019 - 11:28:33 AM
Last modification on : Monday, September 23, 2019 - 5:16:04 PM

File

2019_ICNLSP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02292945, version 1

Collections

Citation

Jean-Christophe Mensonides, Sébastien Harispe, Jacky Montmain, Véronique Thireau. Automatic Detection and Classification of Argument Components using Multi-task Deep Neural Network. 3rd International Conference on Natural Language and Speech Processing, Sep 2019, Trento, Italy. ⟨hal-02292945⟩

Share

Metrics

Record views

35

Files downloads

20