English

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

Computation and Language 2021-03-31 v1

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.

Keywords

Cite

@article{arxiv.2103.15927,
  title  = {Explaining a Neural Attention Model for Aspect-Based Sentiment Classification Using Diagnostic Classification},
  author = {Lisa Meijer and Flavius Frasincar and Maria Mihaela Trusca},
  journal= {arXiv preprint arXiv:2103.15927},
  year   = {2021}
}

Comments

The 36th ACM/SIGAPP Symposium On Applied Computing, Virtual Conference, March 22-March 26, 2021

R2 v1 2026-06-24T00:40:04.264Z