Sentiment Tagging with Partial Labels using Modular Architectures
This work addresses sentiment analysis tasks by reducing labeling effort, but it is incremental as it builds on existing modular and partial label methods.
The paper tackles sentiment analysis by decomposing sequence prediction tasks into sub-tasks with partial labels, using a modular architecture to share information and reduce supervision needs.
Many NLP learning tasks can be decomposed into several distinct sub-tasks, each associated with a partial label. In this paper we focus on a popular class of learning problems, sequence prediction applied to several sentiment analysis tasks, and suggest a modular learning approach in which different sub-tasks are learned using separate functional modules, combined to perform the final task while sharing information. Our experiments show this approach helps constrain the learning process and can alleviate some of the supervision efforts.