InfoLossQA – Characterizing and Recovering Information Loss in Text Simplification (ACL’24)
Text simplification aims to make texts more accessible to a broader audience. Simplification, however, is inherently a lossy process. Additionally, one simplification might not fit all – readers have different background knowledge and information needs. How do we know which information is lost in a simplified version, and can readers help to iteratively recover the information?
InfoLossQA is a framework to identify and recover information loss as question-answer pairs. See the website, demo and paper for more details.
Links