SASS: Data and Methods for Subject Aware Sentence Simplification
This work addresses the need for more targeted simplification in natural language processing, though it is incremental as it builds on existing summarization methods.
The paper tackles the problem of subject-aware sentence simplification by creating a dataset and testing models inspired by abstractive summarization, showing that data augmentation, data masking, and specific model architectures provide a solid baseline for comparison.
Sentence simplification tends to focus on the generic simplification of sentences by making them more readable and easier to understand. This paper provides a dataset aimed at training models that perform subject aware sentence simplifications rather than simplifying sentences as a whole. We also test models on that dataset which are inspired by model architecture used in abstractive summarization. We hand generated portions of the data and augment the dataset by further manipulating those hand written simplifications. Our results show that data-augmentation, data-masking, and model architecture choices used in summarization provide a solid baseline for comparison on subject aware simplification.