Automated Text Simplification

Al-Thanyyan, Suha S.; Azmi, Aqil M.

doi:10.1145/3442695

Cited by 63 publications

(39 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…La segunda consiste en simplificar las estructuras complejas preservando el significado original. Hasta hace poco las soluciones todavía estaban basadas en reglas utilizando etiquetadores y analizadores sintácticos (Al-Thanyyan & Azmi, 2021).…”

Section: Lecturabilidad Y Simplificación De Textosunclassified

Construcción de contenido para un Sistema Tutor Inteligente en idiomas: un estudio piloto con el corpus OneStopEnglish

Escobar-Acevedo

Guerrero-García

2022

Rev. colomb. comput.

View full text Add to dashboard Cite

Durante la adquisición de un idioma extranjero, la lectura representa una de las oportunidades de acercamiento al lenguaje. Sin embargo, los textos inadecuados pueden desencadenar una experiencia contraproducente para un estudiante, por ello, en los cursos regulares, los docentes utilizan su experiencia o la de un equipo editorial para seleccionar las lecturas. En un sistema automático como en un Sistema Tutor Inteligente, es prioritario realizar recomendaciones adecuadas al perfil del alumno. No basta conocer el nivel de idioma del texto, El presente trabajo aplica herramientas para clasificar una muestra de textos extraídos del corpus OneStopEnglish conforme al Marco Común de Referencia Europeo, crea grupos temáticos con análisis semántico latente (LSA), y aplica tres métricas populares de lecturabilidad como un referente para recomendar textos a los estudiantes.

show abstract

Section: Lecturabilidad Y Simplificación De Textosunclassified

Construcción de contenido para un Sistema Tutor Inteligente en idiomas: un estudio piloto con el corpus OneStopEnglish

Escobar-Acevedo

Guerrero-García

2022

Rev. colomb. comput.

View full text Add to dashboard Cite

show abstract

“…The task of TS is similar in nature to other sequence-to-sequence NLP tasks such as machine translation, paraphrase generation [21,17] and most to text summarization. It can be considered as text summarization which can involve selecting sentences from the input text (extractive) or re-writing the input text (abstractive) in order to preserve most of the meaning [7].…”

Section: Related Workmentioning

confidence: 99%

Text Simplification with Autoregressive Models

Fenogenova¹,

Sberbank²

2021

Computational Linguistics and Intellectual Technologies

View full text Add to dashboard Cite

Text Simplification is the task of reducing the complexity of the vocabulary and sentence structure of the text while retaining its original meaning with the goal of improving readability and understanding. We explore the capability of the autoregressive models such as RuGPT3 (Generative Pre-trained Transformer 3 for Russian) to generate high quality simplified sentences. Within the shared task RuSimpleSentEval we present our solution based on different usages of RuGPT3 models. The following setups are described: 1) few-shot unsupervised generation with the RuGPTs models 2) the effect of the size of the training dataset on the downstream performance of fine-tuned model 3) 3 inference strategies 4) the downstream transfer and post-processing procedure using pretrained paraphrasers for Russian. This paper presents the second-place solution on the public leaderboard and the fifth-place solution on the private leaderboard. The proposed method is comparable with the novel state-of-the-art approaches. Additionally, we analyze the performance and discuss the flaws of RuGPTs generation.

show abstract

“…TS is an active NLP research area, like other ongoing research, its techniques have moved away from manually hand-crafted rules towards deep learning techniques (Sikka and Mago, 2020;Al-Thanyyan and Azmi, 2021). Most of these techniques were borrowed from closely related NLP tasks such as Machine Translation (Sikka and Mago, 2020) .…”

Section: Introductionmentioning

confidence: 99%

Towards Arabic Sentence Simplification via Classification and Generative Approaches

Khallaf¹,

Sharoff²

2022

Preprint

View full text Add to dashboard Cite

This paper presents an attempt to build a Modern Standard Arabic (MSA) sentence-level simplification system. We experimented with sentence simplification using two approaches: (i) a classification approach leading to lexical simplification pipelines which use Arabic-BERT, a pre-trained contextualised model, as well as a model of fastText word embeddings; and (ii) a generative approach, a Seq2Seq technique by applying a multilingual Text-to-Text Transfer Transformer mT5. We developed our training corpus by aligning the original and simplified sentences from the internationally acclaimed Arabic novel "Saaq al-Bambuu". We evaluate effectiveness of these methods by comparing the generated simple sentences to the target simple sentences using the BERTScore evaluation metric. The simple sentences produced by the mT5 model achieve P 0.72, R 0.68 and F-1 0.70 via BERTScore, while, combining Arabic-BERT and fastText achieves P 0.97, R 0.97 and F-1 0.97. In addition, we report a manual error analysis for these experiments.

show abstract

Automated Text Simplification

Cited by 63 publications

References 91 publications

Construcción de contenido para un Sistema Tutor Inteligente en idiomas: un estudio piloto con el corpus OneStopEnglish

Construcción de contenido para un Sistema Tutor Inteligente en idiomas: un estudio piloto con el corpus OneStopEnglish

Text Simplification with Autoregressive Models

Towards Arabic Sentence Simplification via Classification and Generative Approaches

Contact Info

Product

Resources

About