Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

12-2017

Abstract

In this paper, we study domain adaptationwith a state-of-the-art hierarchicalneural network for document-level sentimentclassification. We first design a newauxiliary task based on sentiment scoresof domain-independent words. We thenpropose two neural network architecturesto respectively induce document embeddingsand sentence embeddings that workwell for different domains. When thesedocument and sentence embeddings areused for sentiment classification, we findthat with both pseudo and external sentimentlexicons, our proposed methods canperform similarly to or better than severalhighly competitive domain adaptationmethods on a benchmark dataset of productreviews.

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

Proceedings of the 8th International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017 November 27 - December 1

First Page

654

Last Page

663

Publisher

ACL

City or Country

Stroudsburg, PA

Additional URL

http://www.aclweb.org/anthology/I17-1066

Share

COinS