# Leveraging Recursive Processing for Neural-Symbolic Affect-Target Associations

arXiv: https://arxiv.org/abs/2103.03755 · HTML: https://mlsanity.com/paper/2103.03755/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 20 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 2 of 2)

- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)

## Built on by (most cited first, 2 of 2)

- [Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review](https://mlsanity.com/paper/2202.12205/) (2022)
- [Tell Me Why You Feel That Way: Processing Compositional Dependency for Tree-LSTM Aspect Sentiment Triplet Extraction (TASTE)](https://mlsanity.com/paper/2103.05815/) (2021)

## Abstract (arXiv)

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.