We further investigate multi-task training on the related task of sentiment classification, which improves our model’s performance to 55 F1.
In this work, we focus on the domain transfer performance of supervised neural text segmentation in the educational domain.
Based on the insight that humans pay specific attention to movements, we use graphics interchange formats (GIFs) as a pivot to collect parallel sentences from monolingual annotators.
Recent advances in natural language processing (NLP) have the ability to transform how classroom learning takes place.
Word sense induction (WSI), which addresses polysemy by unsupervised discovery of multiple word senses, resolves ambiguities for downstream NLP tasks and also makes word representations more interpretable.