Explaining a Neural Attention Model for Aspect-Based Sentiment Classification Using Diagnostic Classification

L Meijer, Flavius Frasincar, Maria Mihaela Trusca

Research output: Chapter/Conference proceedingConference proceedingAcademicpeer-review

5 Citations (Scopus)

Abstract

Many high performance machine learning models for Aspect-Based Sentiment Classification (ABSC) produce black box models, and therefore barely explain how they classify a certain sentiment value towards an aspect. In this paper, we propose explanation models, that inspect the internal dynamics of a state-of-the-art neural attention model, the LCR-Rot-hop, by using a technique called Diagnostic Classification. Our diagnostic classifier is a simple neural network, which evaluates whether the internal layers of the LCR-Rot-hop model encode useful word information for classification, i.e., the part of speech, the sentiment value, the presence of aspect relation, and the aspect-related sentiment value of words. We conclude that the lower layers in the LCR-Rot-hop model encode the part of speech and the sentiment value, whereas the higher layers represent the presence of a relation with the aspect and the aspect-related sentiment value of words.

Original languageEnglish
Title of host publicationProceedings of the 36th Annual ACM Symposium on Applied Computing, SAC 2021
Pages821-827
Number of pages7
DOIs
Publication statusPublished - 22 Mar 2021

Bibliographical note

Publisher Copyright:
© 2021 ACM.

Research programs

  • ESE - E&MS

Fingerprint

Dive into the research topics of 'Explaining a Neural Attention Model for Aspect-Based Sentiment Classification Using Diagnostic Classification'. Together they form a unique fingerprint.

Cite this