# Gated Convolutional Neural Networks for Domain Adaptation

## TL;DR

This paper demonstrates that Gated Convolutional Neural Networks effectively improve domain adaptation in sentiment analysis by filtering domain-dependent knowledge, outperforming traditional architectures with benefits in parallelization and simplicity.

## Contribution

The paper introduces the use of Gated CNNs for domain adaptation in sentiment analysis, showing their superior performance and efficiency over existing convolutional and recurrent models.

## Key findings

- GCNs outperform traditional CNNs and RNNs in domain adaptation tasks.
- Gated architectures effectively filter domain-specific knowledge.
- GCNs offer computational advantages through parallelization.

## Abstract

Domain Adaptation explores the idea of how to maximize performance on a target domain, distinct from source domain, upon which the classifier was trained. This idea has been explored for the task of sentiment analysis extensively. The training of reviews pertaining to one domain and evaluation on another domain is widely studied for modeling a domain independent algorithm. This further helps in understanding correlation between domains. In this paper, we show that Gated Convolutional Neural Networks (GCN) perform effectively at learning sentiment analysis in a manner where domain dependant knowledge is filtered out using its gates. We perform our experiments on multiple gate architectures: Gated Tanh ReLU Unit (GTRU), Gated Tanh Unit (GTU) and Gated Linear Unit (GLU). Extensive experimentation on two standard datasets relevant to the task, reveal that training with Gated Convolutional Neural Networks give significantly better performance on target domains than regular convolution and recurrent based architectures. While complex architectures like attention, filter domain specific knowledge as well, their complexity order is remarkably high as compared to gated architectures. GCNs rely on convolution hence gaining an upper hand through parallelization.