Representation Learning for Text-level Discourse Parsing
TL
TL;DR
A representation learning approach, in which surface features are transformed into a latent space that facilitates RST discourse parsing, which obtains substantial improvements over the previous state-of-the-art in predicting relations and nuclearity on the RST Treebank.
Abstract
Text-level discourse parsing is notoriously difficult, as distinctions between discourse relations require subtle semantic judgments that are not easily captured using standard features. In this paper, we present a representation learning approach, in which we transform surface features into a latent space that facilitates RST discourse parsing. By combining the machinery of large-margin transition-based structured prediction with representation learning, our method jointly learns to parse discourse while at the same time learning a discourse-driven projection of surface features. The resulting shift-reduce discourse parser obtains substantial improvements over the previous state-of-the-art in predicting relations and nuclearity on the RST Treebank.
References56 items
1
Structured Penalties for Log-Linear Language Models
2
Discriminative Improvements to Distributional Sentence Similarity
3
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
4
Recurrent Convolutional Neural Networks for Discourse Compositionality
5