DeepAI AI Chat
Log In Sign Up

Shallow Domain Adaptive Embeddings for Sentiment Analysis

by   Prathusha K Sarma, et al.
University of Wisconsin-Madison

This paper proposes a way to improve the performance of existing algorithms for text classification in domains with strong language semantics. We propose a domain adaptation layer learns weights to combine a generic and a domain specific (DS) word embedding into a domain adapted (DA) embedding. The DA word embeddings are then used as inputs to a generic encoder + classifier framework to perform a downstream task such as classification. This adaptation layer is particularly suited to datasets that are modest in size, and which are, therefore, not ideal candidates for (re)training a deep neural network architecture. Results on binary and multi-class classification tasks using popular encoder architectures, including current state-of-the-art methods (with and without the shallow adaptation layer) show the effectiveness of the proposed approach.


page 1

page 2

page 3

page 4


Domain Adapted Word Embeddings for Improved Sentiment Classification

Generic word embeddings are trained on large-scale generic corpora; Doma...

Deep Learning and Word Embeddings for Tweet Classification for Crisis Response

Tradition tweet classification models for crisis response focus on convo...

Domain-adaptation of spherical embeddings

Domain adaptation of embedding models, updating a generic embedding to t...

Sequential Domain Adaptation through Elastic Weight Consolidation for Sentiment Analysis

Elastic Weight Consolidation (EWC) is a technique used in overcoming cat...

Attention Regularized Laplace Graph for Domain Adaptation

In leveraging manifold learning in domain adaptation (DA), graph embeddi...

A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation

Recently, DNN model compression based on network architecture design, e....

Large Scale Indexing of Generic Medical Image Data using Unbiased Shallow Keypoints and Deep CNN Features

We propose a unified appearance model accounting for traditional shallow...