Linguistically Regularized LSTMs for Sentiment Classification

Abstract

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.

References in corpus (3)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
• A Convolutional Neural Network for Modelling Sentences

Cited by in corpus (14)

• Investigating Capsule Networks with Dynamic Routing for Text Classification
• Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
• Sentence-State LSTM for Text Representation
• How recurrent networks implement contextual processing in sentiment analysis
• Sentiment Analysis for Sinhala Language using Deep Learning Techniques
• Code-Mixed Sentiment Analysis Using Machine Learning and Neural Network Approaches
• Densely Connected Bidirectional LSTM with Applications to Sentence Classification
• Estimation of Inter-Sentiment Correlations Employing Deep Neural Network Models
• Dual Memory Network Model for Biased Product Review Classification
• Network of Recurrent Neural Networks
• Dual-State Capsule Networks for Text Classification
• Malicious Requests Detection with Improved Bidirectional Long Short-term Memory Neural Networks
• Emotion Correlation Mining Through Deep Learning Models on Natural Language Text
• Thick-Net: Parallel Network Structure for Sequential Modeling