en
Proceedings chapter
Open access
English

Simple, Simpler and Beyond: A Fine-Tuning BERT-Based Approach to Enhance Sentence Complexity Assessment for Text Simplification

Presented at 16-17.12.2023
PublisherACL
First online date2023-12
Abstract

Automatic text simplification models face the challenge of generating outputs that, while being indeed simpler, still retain some complexity. This stems from the inherently relative nature of simplification, wherein a given text is transformed into a relatively simpler version, which does not necessarily equate to simple. We thus aim to propose a finer-grained method to assess sentence complexity in French. Our solution comprises three models, in which two address absolute and relative sentence complexity assessment, while the third focuses on measuring simplicity gain. By employing this triad of models, we aim to offer a comprehensive approach to qualify and quantify sentence simplicity. Our approach utilizes FlauBERT, finetuned for classification and regression tasks. Based on our three-dimensional complexity analysis, we provide the WIVICO dataset, comprising 46,525 aligned complex-simpler pairs, which can be further leveraged to fine-tune large language models to automatically generate simplified texts, or to assess text complexity with greater granularity

eng
Keywords
  • Automatic text simplification
  • Sentence complexity assessment
  • Comparable corpora
Citation (ISO format)
ORMAECHEA GRIJALBA, Lucía et al. Simple, Simpler and Beyond: A Fine-Tuning BERT-Based Approach to Enhance Sentence Complexity Assessment for Text Simplification. In: Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023). [s.l.] : ACL, 2023. p. 14.
Main files (1)
Proceedings chapter (Published version)
accessLevelPublic
Identifiers
  • PID : unige:173944
71views
4downloads

Technical informations

Creation12/18/2023 4:37:58 PM
First validation12/22/2023 8:53:55 AM
Update time12/22/2023 11:07:35 AM
Status update12/22/2023 11:07:35 AM
Last indexation05/06/2024 5:39:36 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack