Non-Compositionality in Sentiment: New Data and Analyses
This work addresses the challenge of handling non-compositional phrases in sentiment analysis for NLP researchers, though it is incremental as it builds on existing sentiment analysis studies.
The paper tackled the problem of non-compositionality in sentiment analysis by creating a new dataset of non-compositionality ratings for 259 phrases, called NonCompSST, and evaluated computational models using this resource.
When natural language phrases are combined, their meaning is often more than the sum of their parts. In the context of NLP tasks such as sentiment analysis, where the meaning of a phrase is its sentiment, that still applies. Many NLP studies on sentiment analysis, however, focus on the fact that sentiment computations are largely compositional. We, instead, set out to obtain non-compositionality ratings for phrases with respect to their sentiment. Our contributions are as follows: a) a methodology for obtaining those non-compositionality ratings, b) a resource of ratings for 259 phrases -- NonCompSST -- along with an analysis of that resource, and c) an evaluation of computational models for sentiment analysis using this new resource.