MultiAzterTest: a Multilingual Analyzer on Multiple Levels of Language for Readability Assessment

Bengoetxea, Kepa; Gonzalez-Dios, Itziar

doi:10.48550/arxiv.2109.04870

Cited by 4 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-Ihardetsi: a Question-Answering system 47 for the area of Science and Technology 48 . -MultiAzterTest: an open source NLP tool which analyses texts on more than 125 linguistic and stylistic features for English, Spanish and Basque 49 and assesses the complexity level (readability) 50 .…”

Section: End User Nlp Products For Basquementioning

confidence: 99%

Natural Language Processing and Language Technologies for the Basque Language

Gonzalez-Dios

Altuna

2022

CED

Self Cite

View full text Add to dashboard Cite

The presence of a language in the digital domain is crucial for its survival, as online communication and digital language resources have become the standard in the last decades and will gain more importance in the coming years. In order to develop advanced systems that are considered the basics for an efficient digital communication (e.g. machine translation systems, text-to-speech and speech-to-text converters and digital assistants), it is necessary to digitalise linguistic resources and create tools. In the case of Basque, scholars have studied the creation of digital linguistic resources and the tools that allow the development of those systems for the last forty years. In this paper, we present an overview of the natural language processing and language technology resources developed for Basque, their impact in the process of making Basque a “digital language” and the applications and challenges in multilingual communication. More precisely, we present the well-known products for Basque, the basic tools and the resources that are behind the products we use every day. Likewise, we would like that this survey serves as a guide for other minority languages that are making their way to digitalisation. Recibido: 05 abril 2022Aceptado: 20 mayo 2022

show abstract

Section: End User Nlp Products For Basquementioning

confidence: 99%

Natural Language Processing and Language Technologies for the Basque Language

Gonzalez-Dios

Altuna

2022

CED

Self Cite

View full text Add to dashboard Cite

show abstract

“…to base our complexity evaluation on recent evidence on sentence and text processing complexity, and thus we have decided to follow the metrics provided by the LeULi model (Gutiérrez-Fandiño, 2022). For the automatic measurement of complexity metrics, we have employed MultiAzterTest (Bengoetxea and Gonzalez-Dios, 2021), an opensource multilingual text analysis tool which examines more than 130 features at various linguistic levels. To calculate word frequencies we have used Python's wordfreq package (Speer et al, 2018).…”

Section: Complexity Assessment Of Irekialf_esmentioning

confidence: 99%

IrekiaLFes: a New Open Benchmark and Baseline Systems for Spanish Automatic Text Simplification

Gonzalez-Dios,

Gutiérrez-Fandiño,

Cumbicus-Pineda

et al. 2022

Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)

View full text Add to dashboard Cite

Automatic Text simplification (ATS) seeks to reduce the complexity of a text for a general or a target audience. In the last years, deep learning methods have become the most used systems in ATS research, but these systems need large and good-quality datasets to be evaluated. Moreover, these data are available on a large scale only for English and in some cases with restrictive licenses. In this paper, we present IrekiaLF_es, an open-license benchmark for Spanish text simplification. It consists of a document-level corpus and a sentence-level test set that has been manually aligned. We also conduct a neurolinguistically-based evaluation of the corpus in order to reveal its suitability for text simplification. This evaluation follows the Lexicon-Unification-Linearity (LeULi) model of neurolinguistic complexity assessment. Finally, we present a set of experiments and baselines of ATS systems in a zero-shot scenario.

show abstract

“…Others have implemented tools that extract readability indices (e.g. lexical diversity, word information, syntactic complexity) and used them as features to train standard machine learning classifiers to estimate a text's readability (Quispesaravia et al, 2016;López-Anguita et al, 2018;Bengoetxea and Gonzalez-Dios, 2021).…”

Section: Introductionmentioning

confidence: 99%

A Benchmark for Neural Readability Assessment of Texts in Spanish

Vásquez-Rodríguez,

Cuenca-Jiménez,

Morales-Esquivel

et al. 2022

Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)

View full text Add to dashboard Cite

We release a new benchmark for Automated Readability Assessment (ARA) of texts in Spanish. We combined existing corpora with suitable texts collected from the Web, thus creating the largest available dataset for ARA of Spanish texts. All data was pre-processed and categorised to allow experimenting with ARA models that make predictions at two (simple and complex) or three (basic, intermediate, and advanced) readability levels, and at two text granularities (paragraphs and sentences). An analysis based on readability indices shows that our proposed datasets groupings are suitable for their designated readability level. We use our benchmark to train neural ARA models based on BERT in zero-shot, few-shot, and crosslingual settings. Results show that either a monolingual or multilingual pre-trained model can achieve good results when fine-tuned in language-specific data. In addition, all models decrease their performance when predicting three classes instead of two, showing opportunities for the development of better ARA models for Spanish with existing resources.

show abstract

MultiAzterTest: a Multilingual Analyzer on Multiple Levels of Language for Readability Assessment

Cited by 4 publications

References 26 publications

Natural Language Processing and Language Technologies for the Basque Language

Natural Language Processing and Language Technologies for the Basque Language

IrekiaLFes: a New Open Benchmark and Baseline Systems for Spanish Automatic Text Simplification

A Benchmark for Neural Readability Assessment of Texts in Spanish

Contact Info

Product

Resources

About