Comparing Word Representations for Implicit Discourse Relation Classification

Chloé Braud 1, * Pascal Denis 2
* Auteur correspondant
1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
Inria Paris-Rocquencourt, UPD7 - Université Paris Diderot - Paris 7
2 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : This paper presents a detailed comparative framework for assessing the usefulness of unsupervised word representations for identifying so-called implicit discourse relations. Specifically, we compare standard one-hot word pair representations against low-dimensional ones based on Brown clusters and word embeddings. We also consider various word vector combination schemes for deriving discourse segment representations from word vectors, and compare representations based either on all words or limited to head words. Our main finding is that denser representations systematically outperform sparser ones and give state-of-the-art performance or above without the need for additional hand-crafted features.
Type de document :
Communication dans un congrès
Empirical Methods in Natural Language Processing (EMNLP 2015), Sep 2015, Lisbonne, Portugal. Empirical Methods in Natural Language Processing, 2015
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01185927
Contributeur : Chloé Braud <>
Soumis le : mardi 25 août 2015 - 15:57:32
Dernière modification le : mardi 3 juillet 2018 - 11:33:59
Document(s) archivé(s) le : jeudi 26 novembre 2015 - 13:51:10

Fichier

cbraud_pdenis_emnlp15.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01185927, version 1

Citation

Chloé Braud, Pascal Denis. Comparing Word Representations for Implicit Discourse Relation Classification. Empirical Methods in Natural Language Processing (EMNLP 2015), Sep 2015, Lisbonne, Portugal. Empirical Methods in Natural Language Processing, 2015. 〈hal-01185927〉

Partager

Métriques

Consultations de la notice

485

Téléchargements de fichiers

351