Litcius/Paper detail

CVAE-based Re-anchoring for Implicit Discourse Relation Classification

Zujun Dou, Yu Hong, Yu Sun, Guodong Zhou

202110 citationsDOIOpen Access PDF

Abstract

Training implicit discourse relation classifiers suffers from data sparsity. Variational AutoEncoder (VAE) appears to be the proper solution. It is because that VAE is able to automatically generate inexhaustible varying samples by self supervision, and facilitates data augmentation. However, our experiments show that the utilization of VAE results in severe performance degradation. We ascribe this phenomenon to erroneous sampling. To address the issue, we use Conditional VAE (CVAE) to estimate the risk of erroneous sampling. Moreover, we develop a re-anchoring method which migrates the anchor of sampling area of VAE to reduce the risk. The experiments on PDTB v2.0 demonstrate that, compared to the RoBERTabased baseline, re-anchoring yields substantial improvements. In addition, we prove that re-anchoring can cooperate with other auxiliary strategies (transfer learning and interactive attention mechanism) to further improve the classification performance.

Topics & Concepts

AnchoringAutoencoderComputer scienceArtificial intelligenceClassifier (UML)Machine learningSampling (signal processing)ContingencyContingency tableRelation (database)Pattern recognition (psychology)Data miningArtificial neural networkCognitive sciencePsychologyLinguisticsFilter (signal processing)PhilosophyComputer visionTopic ModelingNatural Language Processing TechniquesSentiment Analysis and Opinion Mining