Linguistically Regularized LSTMs for Sentiment Classification

11/12/2016
by   Qiao Qian, et al.
0

Sentiment understanding has been a long-term goal of AI in the past decades. This paper deals with sentence-level sentiment classification. Though a variety of neural network models have been proposed very recently, however, previous models either depend on expensive phrase-level annotation, whose performance drops substantially when trained with only sentence-level annotation; or do not fully employ linguistic resources (e.g., sentiment lexicons, negation words, intensity words), thus not being able to produce linguistically coherent representations. In this paper, we propose simple models trained with sentence-level annotation, but also attempt to generating linguistically coherent representations by employing regularizers that model the linguistic role of sentiment lexicons, negation words, and intensity words. Results show that our models are effective to capture the sentiment shifting effect of sentiment, negation, and intensity words, while still obtain competitive results without sacrificing the models' simplicity.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/13/2018

A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification

Deep learning approaches for sentiment classification do not fully explo...
research
10/23/2020

Attention Transfer Network for Aspect-level Sentiment Classification

Aspect-level sentiment classification (ASC) aims to detect the sentiment...
research
12/04/2018

Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models

Neural sequence models have achieved great success in sentence-level sen...
research
11/06/2018

WordNet-feelings: A linguistic categorisation of human feelings

In this article, we present the first in depth linguistic study of human...
research
12/23/2019

Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network

Most recent existing aspect-term level sentiment analysis (ATSA) approac...
research
12/03/2015

Effective LSTMs for Target-Dependent Sentiment Classification

Target-dependent sentiment classification remains a challenge: modeling ...
research
09/26/2019

Rethinking Text Attribute Transfer: A Lexical Analysis

Text attribute transfer is modifying certain linguistic attributes (e.g....

Please sign up or login with your details

Forgot password? Click here to reset