Evaluating Discourse in Structured Text Representations

06/04/2019
by   Elisa Ferracane, et al.
0

Discourse structure is integral to understanding a text and is helpful in many NLP tasks. Learning latent representations of discourse is an attractive alternative to acquiring expensive labeled discourse data. Liu and Lapata (2018) propose a structured attention mechanism for text classification that derives a tree over a text, akin to an RST discourse tree. We examine this model in detail, and evaluate on additional discourse-relevant tasks and datasets, in order to assess whether the structured attention improves performance on the end task and whether it captures a text's discourse structure. We find the learned latent trees have little to no structure and instead focus on lexical cues; even after obtaining more structured trees with proposed model modifications, the trees are still far from capturing discourse structure when compared to discourse dependency trees from an existing discourse parser. Finally, ablation studies show the structured attention provides little benefit, sometimes even hurting performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2017

Neural Discourse Structure for Text Categorization

We show that discourse structure, as defined by Rhetorical Structure The...
research
11/13/2018

Discourse in Multimedia: A Case Study in Information Extraction

To ensure readability, text is often written and presented with due form...
research
12/17/2020

Unsupervised Learning of Discourse Structures using a Tree Autoencoder

Discourse information, as postulated by popular discourse theories, such...
research
10/18/2022

Unsupervised Inference of Data-Driven Discourse Structures using a Tree Auto-Encoder

With a growing need for robust and general discourse structures in many ...
research
06/04/2021

W-RST: Towards a Weighted RST-style Discourse Framework

Aiming for a better integration of data-driven and linguistically-inspir...
research
11/16/2019

Improved Document Modelling with a Neural Discourse Parser

Despite the success of attention-based neural models for natural languag...
research
04/18/2017

Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees

Prominent applications of sentiment analysis are countless, covering are...

Please sign up or login with your details

Forgot password? Click here to reset