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… (More)

Topics

4 Figures and Tables

Statistics

02040201520162017
Citations per Year

Citation Velocity: 20

Averaging 20 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.