Multitask Learning for Class-Imbalanced Discourse Classification

01/02/2021
by   Alexander Spangher, et al.
2

Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures. In this work, we perform an extensive analysis on sentence-level classification approaches for the News Discourse dataset, one of the largest high-level semantic discourse datasets recently published. We show that a multitask approach can improve 7 state-of-the-art benchmarks, due in part to label corrections across tasks, which improve performance for underrepresented classes. We also offer a comparative review of additional techniques proposed to address resource-poor problems in NLP, and show that none of these approaches can improve classification accuracy in such a setting.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

page 16

12/12/2021

Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation

RST-style discourse parsing plays a vital role in many NLP tasks, reveal...
06/02/2020

DiscSense: Automated Semantic Analysis of Discourse Markers

Discourse markers ( by contrast, happily, etc.) are words or phrases th...
03/28/2019

Mining Discourse Markers for Unsupervised Sentence Representation Learning

Current state of the art systems in NLP heavily rely on manually annotat...
03/28/2019

Imbalanced Sentiment Classification Enhanced with Discourse Marker

Imbalanced data commonly exists in real world, espacially in sentiment-r...
05/04/2021

Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media

Discourse relations are typically modeled as a discrete class that chara...
09/10/2021

Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations

Current language models are usually trained using a self-supervised sche...
04/03/2019

Learning Outside the Box: Discourse-level Features Improve Metaphor Identification

Most current approaches to metaphor identification use restricted lingui...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.