Simple is not Enough: Document-level Text Simplification using Readability and Coherence
Published in arXiv preprint., 2024
We present a coherence-aware evaluation of document-level Text Simplification (TS), an approach that has not been considered in TS so far. We improve current TS sentence-based models to support a multi-sentence setting and the implementation of a state-of-the-art neural coherence model for simplification quality assessment. We enhanced English sentence simplification neural models for document-level simplification using 136,113 paragraph-level samples from both the general and medical domains to generate multiple sentences. Additionally, we use document-level simplification, readability and coherence metrics for evaluation. Our contributions include the introduction of coherence assessment into simplification evaluation with the automatic evaluation of 34,052 simplifications, a fine-tuned state-of-the-art model for document-level simplification, a coherence-based analysis of our results and a human evaluation of 300 samples that demonstrates the challenges encountered when moving towards document-level simplification.
Recommended citation: Vásquez-Rodríguez, L., Nguyen, N. T., Przybyła, P., Shardlow, M., & Ananiadou, S. (2024). Simple is not Enough: Document-level Text Simplification using Readability and Coherence. arXiv preprint arXiv:2412.18655.
Recommended citation: Vásquez-Rodríguez, L., Nguyen, N. T., Przybyła, P., Shardlow, M., & Ananiadou, S. (2024). Simple is not Enough: Document-level Text Simplification using Readability and Coherence. arXiv preprint arXiv:2412.18655.
Download Paper