Linguistically Regularized LSTMs for Sentiment Classification
This work addresses sentiment classification for natural language processing applications, offering an incremental improvement by integrating linguistic resources without requiring expensive phrase-level annotations.
The paper tackles sentence-level sentiment classification by proposing models that use sentence-level annotation and linguistic regularizers to capture sentiment, negation, and intensity words, resulting in competitive performance while maintaining model simplicity.
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.