We examine the effect of domain-specific external knowledge variations on deep large scale language model performance.
As labeling schemas evolve over time, small differences can render datasets following older schemas unusable.
Ranked #1 on Text Classification on NewsDiscourse
Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures.
While previous sentiment analysis research has concentrated on the interpretation of explicitly stated opinions and attitudes, this work initiates the computational study of a type of opinion implicature (i. e., opinion-oriented inference) in text.