Analysing Zero-Shot Readability-Controlled Sentence Simplification
Readability-controlled text simplification (RCTS) rewrites texts to lower readability levels while preserving their meaning. RCTS models often depend on parallel corpora with readability annotations on both source and target sides. Such datasets are scarce and difficult to curate, especially at the sentence level. To reduce reliance on parallel data, we explore using instruction-tuned large language models for zero-shot RCTS. Through automatic and manual evaluations, we examine: (1) how different types of contextual information affect a model's ability to generate sentences with the desired readability, and (2) the trade-off between achieving target readability and preserving meaning. Results show that all tested models struggle to simplify sentences (especially to the lowest levels) due to models' limitations and characteristics of the source sentences that impede adequate rewriting. Our experiments also highlight the need for better automatic evaluation metrics tailored to RCTS, as standard ones often misinterpret common simplification operations, and inaccurately assess readability and meaning preservation.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceText SimplificationSimilar Papers 제목 키워드 기반
Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models
Text simplification is a common task where the text is adapted to make it easier to understand. Similarly, text elaboration can make a passage more sophisticated, offering a method to control the complexity of reading co…
Language ModellingReading ComprehensionText SimplificationZero-shot Large Language Models for Automatic Readability Assessment
Unsupervised automatic readability assessment (ARA) methods have important practical and research applications (e.g., ensuring medical or educational materials are suitable for their target audiences). In this paper, we …
Simple is not Enough: Document-level Text Simplification using Readability and Coherence
In this paper, we present the SimDoc system, a simplification model considering simplicity, readability, and discourse aspects, such as coherence. In the past decade, the progress of the Text Simplification (TS) field ha…
SentenceText SimplificationFrom Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences
Current computational approaches for analysing or generating code-mixed sentences do not explicitly model ``naturalness'' or ``acceptability'' of code-mixed sentences, but rely on training corpora to reflect distribution…
DecoderGenerating Educational Materials with Different Levels of Readability using LLMs
This study introduces the leveled-text generation task, aiming to rewrite educational materials to specific readability levels while preserving meaning. We assess the capability of GPT-3.5, LLaMA-2 70B, and Mixtral 8x7B,…
MisinformationText Generation