Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA
This work addresses the need for better evaluation methods in text simplification for researchers and developers, though it is incremental as it builds on existing evaluation frameworks.
The authors tackled the problem of evaluating text simplification systems by introducing SALSA, an edit-based human annotation framework with 21 edit types, and collected 19K annotations to reveal differences in strategies between models and humans, finding that GPT-3.5 makes more quality edits than humans but still has frequent errors.
Large language models (e.g., GPT-4) are uniquely capable of producing highly rated text simplification, yet current human evaluation methods fail to provide a clear understanding of systems' specific strengths and weaknesses. To address this limitation, we introduce SALSA, an edit-based human annotation framework that enables holistic and fine-grained text simplification evaluation. We develop twenty one linguistically grounded edit types, covering the full spectrum of success and failure across dimensions of conceptual, syntactic and lexical simplicity. Using SALSA, we collect 19K edit annotations on 840 simplifications, revealing discrepancies in the distribution of simplification strategies performed by fine-tuned models, prompted LLMs and humans, and find GPT-3.5 performs more quality edits than humans, but still exhibits frequent errors. Using our fine-grained annotations, we develop LENS-SALSA, a reference-free automatic simplification metric, trained to predict sentence- and word-level quality simultaneously. Additionally, we introduce word-level quality estimation for simplification and report promising baseline results. Our data, new metric, and annotation toolkit are available at https://salsa-eval.com.