# Deep Memory Networks for Attitude Identification

## TL;DR

This paper introduces AttNet, an end-to-end deep memory network that jointly performs target detection and sentiment classification for attitude identification, outperforming previous methods by modeling subtask interactions.

## Contribution

The paper proposes a novel deep memory network architecture that integrates target detection and polarity classification into a unified model, capturing their interactions.

## Key findings

- AttNet outperforms existing methods in attitude identification tasks.
- Joint modeling improves accuracy over separate subtask approaches.
- Shared representations vary for different targets, enhancing model flexibility.

## Abstract

We consider the task of identifying attitudes towards a given set of entities from text. Conventionally, this task is decomposed into two separate subtasks: target detection that identifies whether each entity is mentioned in the text, either explicitly or implicitly, and polarity classification that classifies the exact sentiment towards an identified entity (the target) into positive, negative, or neutral. Instead, we show that attitude identification can be solved with an end-to-end machine learning architecture, in which the two subtasks are interleaved by a deep memory network. In this way, signals produced in target detection provide clues for polarity classification, and reversely, the predicted polarity provides feedback to the identification of targets. Moreover, the treatments for the set of targets also influence each other -- the learned representations may share the same semantics for some targets but vary for others. The proposed deep memory network, the AttNet, outperforms methods that do not consider the interactions between the subtasks or those among the targets, including conventional machine learning methods and the state-of-the-art deep learning models.