Comparing Word Representations for Implicit Discourse Relation Classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Comparing Word Representations for Implicit Discourse Relation Classification

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.
Fichier principal
Vignette du fichier
cbraud_pdenis_emnlp15.pdf (243.57 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01185927 , version 1 (25-08-2015)

Identifiers

  • HAL Id : hal-01185927 , version 1

Cite

Chloé Braud, Pascal Denis. Comparing Word Representations for Implicit Discourse Relation Classification. Empirical Methods in Natural Language Processing (EMNLP 2015), Sep 2015, Lisbonne, Portugal. ⟨hal-01185927⟩
422 View
412 Download

Share

Gmail Facebook Twitter LinkedIn More