RastrOS Project: Natural Language Processing contributions to the development of an eye-tracking corpus with predictability norms for Brazilian Portuguese

Abstract

This article presents RastrOS, a new eye-tracking corpus of eye movement data from university students during silent reading of paragraphs of texts in Brazilian Portuguese (BP). The article shows the potential of the corpus for natural language processing (NLP) using it to evaluate the sentence complexity prediction task in BP and it also focuses on the description of NLP resources and methods developed to create the corpus. Specifically, we present: (i) the method used to select the corpus paragraphs from large corpora, using linguistic metrics and clustering algorithms; (ii) the platform for collecting the Cloze test, which is also responsible for creating the project datasets, and (iii) the hybrid semantic similarity method, based on word embedding models and contextualised word representations, used to generate semantic predictability norms. RastrOS can be downloaded from the open science framework repository with the computational infrastructure mentioned above. Datasets with predictability norms of 393 participants and eye-tracking data of 37 participants are available in the OSF repository for this work ( https://osf.io/9jxg3/ ).

Abordagem baseada em Aumento de Dados para Avaliação Automática de Leiturabilidade

“…Para isto, foi desenvolvido um corpus combinado, formado por textos classificados conforme o público-alvo da revista ou jornal de origem. O melhor classificadorLeal (2019) avaliou métodos de predição de complexidade de frases para o PB.Para isto, foram criados dois corpora, um com sentenças alinhadas peloPorSimples, o PorSimplesSent (LEAL et al, 2018), e outro com métricas de rastreamento ocular e normas de previsibilidade para estudantes de nível superior, denominado RastrOS(LEAL et al, 2022b). Foi considerada a versão mais recente da ferramenta NILC-Metrix(LEAL et al, 2021) (com 200 métricas), bem como abordagens de transferência de aprendizado com adição das métricas de rastreamento ocular Leal (2019).…”