Search 250 million research papers

Text Simplification

For Information-Seeking Applications, Beata Beigman Klebanov, Kevin Knight et al. · 2004

Cited by 0

Cognitive Simplification Operations Improve Text Simplification

Eytan Chamovitz, Omri Abend · arXiv (Cornell University) · 2022

Text Simplification (TS) is the task of converting a text into a form that is easier to read while maintaining the meaning of the original text. A sub-task of TS is Cognitive Simplification (CS), converting text to a form that is readily understood by people with cognitive disabilities without rendering it childish or simplistic. This sub-task has yet to be explored with neural methods in NLP, and resources for it are scarcely available. In this paper, we present a method for incorporating knowledge from the cognitive accessibility domain into a TS model, by introducing an inductive bias regarding what simplification operations to use. We show that by adding this inductive bias to a TS-trained model, it is able to adapt better to CS without ever seeing CS data, and outperform a baseline model on a traditional TS benchmark. In addition, we provide a novel test dataset for CS, and analyze the differences between CS corpora and existing TS corpora, in terms of how simplification operations are applied.

Cited by 1Open access

Cognitive Simplification Operations Improve Text Simplification

Eytan Chamovitz, Omri Abend · 2022

Text Simplification (TS) is the task of converting a text into a form that is easier to read while maintaining the meaning of the original text. A sub-task of TS is Cognitive Simplification (CS), converting text to a form that is readily understood by people with cognitive disabilities without rendering it childish or simplistic. This sub-task has yet to be explored with neural methods in NLP, and resources for it are scarcely available. In this paper, we present a method for incorporating knowledge from the cognitive accessibility domain into a TS model, by introducing an inductive bias regarding what simplification operations to use. We show that by adding this inductive bias to a TS-trained model, it is able to adapt better to CS without ever seeing CS data, and outperform a baseline model on a traditional TS benchmark. In addition, we provide a novel test dataset for CS, and analyze the differences between CS corpora and existing TS corpora, in terms of how simplification operations are applied.

Cited by 4Open access

Controllable Text Simplification

Li, Zihao · e-space (Manchester Metropolitan University) · 2024

Text simplification is a tool that enhances the accessibility of text at both lexical
\nand syntactical levels. It aids individuals in comprehending complex texts more
\neasily, particularly children, students, and people with reading difficulties. This thesis
\naims to investigate the effects, limitations, and potential enhancements of the
\ncurrent state-of-the-art method in text simplification.
\nThe thesis consists of three main experiments and addresses the challenges in
\ntext simplification. In the first experiment, we focused on the various needs in text
\nsimplification, explored the impact of the control mechanism in text simplification,
\nre-implemented the state-of-the-art system with less computation power, and redesigned
\nthe tokenization and quantization for the control mechanism to improve
\nthe performance by up to 0.5 points in the metrics. In the second experiment, we
\naddressed the impact of text style in text simplification tasks in different domains,
\nconstructed a genre-specific test scenario focused on coronavirus, verified the effect
\nof the genre in text simplification tasks, and compared these models with large
\nlanguage models (e.g. ChatGPT) as the generic model. In the final experiment, we
\naddressed the lack of adaptation ability in the system, fine-tuned models to predict
\nthe value of four control tokens, integrated these predictors with the current system,
\nand thereby enhanced the practicality and popularity of controllable text simplification
\nsystems.
\nAs a result, we explored the mechanism of control tokens, verified the effectiveness
\nof controllable text simplification in the genre-specific corpus, and improved
\nthe overall performance and adaptability of the controllable text simplification system.

Cited by 0Open access

Text Simplification Examples

Anamaria Briciu · Figshare · 2026

Text simplification examples produced by LLMs (Copilot).

Cited by 0Open access

Text Simplification Examples

Anamaria Briciu · Figshare · 2026

Text simplification examples produced by LLMs (Copilot).

Cited by 0Open access

Text Simplification and Complexity Simple Language Automatic Text Simplification Evaluating Simplified Texts,What is Text Simplification

Advaith Siddharthan, Katie Melua, Simon Singh · 2016

We are twelve billion light years from the edge, That’s a guess, No-one can ever say it’s true, But I know that I will always be with you.

Cited by 0

Unsupervised Neural Text Simplification

Sai Surya, Abhijit Mishra, Anirban Laha et al. · 2019

The paper presents a first attempt towards unsupervised neural text simplification that relies only on unlabeled text corpora. The core framework is composed of a shared encoder and a pair of attentional-decoders, crucially assisted by discrimination-based losses and denoising. The framework is trained using unlabeled text collected from en-Wikipedia dump. Our analysis (both quantitative and qualitative involving human evaluators) on public test data shows that the proposed model can perform text-simplification at both lexical and syntactic levels, competitive to existing supervised methods. It also outperforms viable unsupervised baselines. Adding a few labeled pairs helps improve the performance further.

Cited by 76Open access

Investigating Text Simplification Evaluation

Association for Computational Linguistics 2021, Sophia Ananiadou, Guzhova Ep et al. · Open MIND · 2021

Modern text simplification (TS) heavily relies on the availability of gold standard data to build machine learning models. However, existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments. Additionally, evaluation is usually performed by using metrics such as BLEU or SARI to compare system output to the gold standard. A major limitation is that these metrics do not match human judgements and the performance on different datasets and linguistic phenomena vary greatly. Furthermore, our research shows that the test and training subsets of parallel datasets differ significantly. In this work, we investigate existing TS corpora, providing new insights that will motivate the improvement of existing state-of-the-art TS evaluation methods. Our contributions include the analysis of TS corpora based on existing modifications used for simplification and an empirical study on TS models performance by using better-distributed datasets. We demonstrate that by improving the distribution of TS datasets, we can build more robust TS models.

Cited by 0

Syntactic simplification of text

Canning, Y.M. · OpenGrey (Institut de l'Information Scientifique et Technique) · 2002

Available from British Library Document Supply Centre-DSC:DXN048910 / BLDSC - British Library Document Supply Centre

Cited by 0

Multilingual adaptative text simplification

Sheang, Kim Cheng · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya) · 2023

Reading is an essential skill that plays a crucial role in our daily lives. It allows us to access information, gain knowledge, expand our understanding of the world around us, and build the foundation for learning, communication, and personal growth. However, many texts we encounter day after day often contain complex words or syntactic structures that can cause reading difficulties for certain groups of people; this motivates the need for Automatic Text Simplification (ATS). ATS is a Natural Language Processing (NLP) task that aims to reduce the linguistic complexity of a text while preserving its original information and meaning. It involves various operations, such as replacing complex words with simpler synonyms, splitting long sentences into shorter ones, and reorganizing the structure of the text. The goal of ATS is to make texts more accessible and understandable to a broader audience, including non-native speakers, children, and individuals with Dyslexia, Autism, Aphasia, Intellectual Disabilities, and Deaf and Hard of Hearing. In this work, we will discuss our proposed methods for Complex Word Identification (CWI), Lexical Simplification (LS), and Sentence Simplification (SS) in order to help improve reading comprehension. For CWI, we propose several systems based on different machine learning algorithms, such as Convolutional Neural Networks, CatBoost, and XGBoost with word embeddings and feature-engineered for identifying complex words in English, Spanish, German, and French texts. For LS, we propose two systems, monolingual English and multilingual system supporting English, Spanish, and Portuguese. For SS, we propose several systems to simplify English and Spanish texts. In both LS and SS, we explore the use of transfer learning and controllable mechanism, where the transfer learning help create the model that requires less amount of training data, and the controllable mechanism gives us the ability to adjust the outputs based on our preference, especially for different target audiences.

Cited by 0Open access

Unsupervised Statistical Text Simplification

Jipeng Qiang, Xindong Wu · IEEE Transactions on Knowledge and Data Engineering · 2019

Most recent approaches for Text Simplification (TS) have drawn on insights from machine translation to learn simplification rewrites from the monolingual parallel corpus of complex and simple sentences, yet their effectiveness strongly relies on large amounts of parallel sentences. However, there has been a serious problem haunting TS for decades, that is, the availability of parallel TS corpora is scarce or not fit for the learning task. In this paper, we will focus on one especially useful and challenging problem of unsupervised TS without a single parallel sentence. To the best of our knowledge, we present the first unsupervised text simplification system based on phrase-based machine translation system, which leverages a careful initialization of phrase tables and language models. On the widely used WikiLarge and WikiSmall benchmarks, our system respectively obtains 39.08 and 25.12 SARI points, even outperforms some supervised baselines.

Cited by 22

Context-Preserving Text Simplification

Christina Niklaus, Matthias Cetto, André Freitas et al. · arXiv (Cornell University) · 2021

We present a context-preserving text simplification (TS) approach that recursively splits and rephrases complex English sentences into a semantic hierarchy of simplified sentences. Using a set of linguistically principled transformation patterns, input sentences are converted into a hierarchical representation in the form of core sentences and accompanying contexts that are linked via rhetorical relations. Hence, as opposed to previously proposed sentence splitting approaches, which commonly do not take into account discourse-level aspects, our TS approach preserves the semantic relationship of the decomposed constituents in the output. A comparative analysis with the annotations contained in the RST-DT shows that we are able to capture the contextual hierarchy between the split sentences with a precision of 89% and reach an average precision of 69% for the classification of the rhetorical relations that hold between them.

Cited by 6Open access

Coreference-Based Text Simplification

Rodrigo Wilkens, Amalia Todiraşcu, Bruno Oberlé · HAL (Le Centre pour la Communication Scientifique Directe) · 2020

Text simplification aims at adapting documents to make them easier to read by a given audience. Usually, simplification systems consider only lexical and syntactic levels, and, moreover, are often evaluated at the sentence level. Thus, studies on the impact of simplification in text cohesion are lacking. Some works add coreference resolution in their pipeline to address this issue. In this paper, we move forward in this direction and present a rule-based system for automatic text simplification, aiming at adapting French texts for dyslexic children. The architecture of our system takes into account not only lexical and syntactic but also discourse information, based on coreference chains. Our system has been manually evaluated in terms of grammaticality and cohesion. We have also built and used an evaluation corpus containing multiple simplification references for each sentence. It has been annotated by experts following a set of simplification guidelines, and can be used to run automatic evaluation of other simplification systems. Both the system and the evaluation corpus are freely available.

Cited by 3

Investigating Text Simplification Evaluation

Laura Vásquez-Rodríguez, Matthew Shardlow, Piotr Przybyła et al. · 2021

Modern text simplification (TS) heavily relies on the availability of gold standard data to build machine learning models. However, existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments. Additionally, evaluation is usually performed by using metrics such as BLEU or SARI to compare system output to the gold standard. A major limitation is that these metrics do not match human judgements and the performance on different datasets and linguistic phenomena vary greatly. Furthermore, our research shows that the test and training subsets of parallel datasets differ significantly. In this work, we investigate existing TS corpora, providing new insights that will motivate the improvement of existing state-ofthe-art TS evaluation methods. Our contributions include the analysis of TS corpora based on existing modifications used for simplification and an empirical study on TS models performance by using better-distributed datasets. We demonstrate that by improving the distribution of TS datasets, we can build more robust TS models.

Cited by 6Open access

Investigating Text Simplification Evaluation

Laura Vásquez-Rodríguez, Matthew Shardlow, Piotr Przybyła et al. · arXiv (Cornell University) · 2021

Modern text simplification (TS) heavily relies on the availability of gold standard data to build machine learning models. However, existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments. Additionally, evaluation is usually performed by using metrics such as BLEU or SARI to compare system output to the gold standard. A major limitation is that these metrics do not match human judgements and the performance on different datasets and linguistic phenomena vary greatly. Furthermore, our research shows that the test and training subsets of parallel datasets differ significantly. In this work, we investigate existing TS corpora, providing new insights that will motivate the improvement of existing state-of-the-art TS evaluation methods. Our contributions include the analysis of TS corpora based on existing modifications used for simplification and an empirical study on TS models performance by using better-distributed datasets. We demonstrate that by improving the distribution of TS datasets, we can build more robust TS models.

Cited by 0Open access

Text simplification in Czech

Karolína Burešová · Digital Repository (National Repository of Grey Literature) · 2017

This thesis deals with text simplification in Czech, in particular with lexical simplification. Several strategies of complex word identification, substitution generation and substitution ranking are implemented and evaluated. Substitution generation is attempted both in a dictionary-based manner and in an embedding- based manner. Some experiments involving people are also presented, the experiments aim at gaining an in- sight into perceived simplicity/complexity and its factors. The experiments conducted and evaluated include sentence pair comparison and manual text simplification. Both the evaluation results of various strategies and the outcomes of experiments involving humans are described and some future work is suggested. 1

Cited by 0

Investigating Text Simplification Evaluation

Association for Computational Linguistics 2021, Ananiadou, Sophia, Przybyła, Piotr et al. · Underline Science Inc. · 2021

Modern text simplification (TS) heavily relies on the availability of gold standard data to build machine learning models. However, existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments. Additionally, evaluation is usually performed by using metrics such as BLEU or SARI to compare system output to the gold standard. A major limitation is that these metrics do not match human judgements and the performance on different datasets and linguistic phenomena vary greatly. Furthermore, our research shows that the test and training subsets of parallel datasets differ significantly. In this work, we investigate existing TS corpora, providing new insights that will motivate the improvement of existing state-of-the-art TS evaluation methods. Our contributions include the analysis of TS corpora based on existing modifications used for simplification and an empirical study on TS models performance by using better-distributed datasets. We demonstrate that by improving the distribution of TS datasets, we can build more robust TS models.

Cited by 0Open access

Text Simplification for Lithuanian

Justina Mandravickaitė, Eglė Rimkienė, Danguolė Kotryna Kapkan et al. · Communications in computer and information science · 2025

Cited by 0

Text simplification for children

Jan De Belder, Marie‐Francine Moens · Lirias (KU Leuven) · 2010

The goal in this paper is to automatically transform text into a simpler text, so that it is easier to understand by children. We perform syntactic simplification, i.e. the splitting of sentences, and lexical simplification, i.e. replacing difficult words with easier synonyms. We test the performance of this approach for each component separately on a per sentence basis, and globally with the automatic construction of simplified news articles and encyclopedia articles. By including information from a language model in the lexical simplification step, we obtain better results over a baseline method. The syntactic simplification shows that some phenomena are hard to recognize by a parser, and that errors are often introduced. Although the reading difficulty goes down, it still doesn’t reach the required level needed for young children.

Cited by 128Open access