Leveraging Recursive Processing for Neural-Symbolic Affect-Target Associations

TL;DR

This paper introduces a hybrid neural-symbolic system using Dependency Tree-LSTM to improve the accuracy and interpretability of affect-target association in natural language, aiding emotional understanding in social robots.

Contribution

It presents a novel recursive neural network approach that combines neural and symbolic methods for affect-target association, enhancing interpretability and accuracy.

Findings

Higher accuracy compared to sequential methods

Improved interpretability of affect-target associations

Effective in aspect-based sentiment analysis

Abstract

Explaining the outcome of deep learning decisions based on affect is challenging but necessary if we expect social companion robots to interact with users on an emotional level. In this paper, we present a commonsense approach that utilizes an interpretable hybrid neural-symbolic system to associate extracted targets, noun chunks determined to be associated with the expressed emotion, with affective labels from a natural language expression. We leverage a pre-trained neural network that is well adapted to tree and sub-tree processing, the Dependency Tree-LSTM, to learn the affect labels of dynamic targets, determined through symbolic rules, in natural language. We find that making use of the unique properties of the recursive network provides higher accuracy and interpretability when compared to other unstructured and sequential methods for determining target-affect associations in an aspect-based sentiment analysis task.