RDF2PT: Generating Brazilian Portuguese Texts from RDF Data

RDF2PT: Generating Brazilian Portuguese Texts from RDF Data Diego Moussallem1,2, Thiago Castro Ferreira 2, Marcos Zampieri3, Maria Claudia Cavalcanti4, Geraldo Xex´eo5, Mariana Neves6, Axel-Cyrille Ngonga Ngomo1,7 1University of Leipzig, Germany, 2Tilburg University, The Netherlands, 3University of Wolverhampton, United Kingdom, 4Military Institute of Engineering - Brazil, 5Federal University of Rio de Janeiro - Brazil, 6German Federal Institute for Risk Assessment - Germany 7Paderborn University, Germany 1lastname@informatik.uni-leipzig.de Abstract The generation of natural language from Resource Description Framework (RDF) data has recently gained significant attention due to the continuous growth of Linked Data. A number of these approaches generate natural language in languages other than English, however, no work has been proposed to generate Brazilian Portuguese texts out of RDF. We address this research gap by presenting RDF2PT, an approach that verbalizes RDF data to Brazilian Portuguese language. We evaluated RDF2PT in an open questionnaire with 44 native speakers divided into experts and non-experts. Our results suggest that RDF2PT is able to generate text which is similar to that generated by humans and can hence be easily understood. Keywords: natural language generation, verbalization, semantic web 1. Introduction Natural Language Generation (NLG) is the process of gen- erating coherent natural language text from non-linguistic data (Reiter and Dale, 2000). Despite community agree- ment on the actual text and speech output of these sys- tems, there is far less consensus on what the input should be (Gatt and Krahmer, 2017). A large number of inputs have been taken for NLG systems, including images (Xu et al., 2015), numeric data (Gkatzia et al., 2014), seman- tic representations (Theune et al., 2001) and Semantic Web (SW) data (Ngonga Ngomo et al., 2013; Bouayad-Agha et al., 2014). Presently, the generation of natural language from SW, more precisely from RDF data, has gained substantial atten- tion (Bouayad-Agha et al., 2014; Staykova, 2014). Some challenges have been proposed to investigate the quality of automatically generated texts from RDF (Colin et al., 2016). Moreover, RDF has demonstrated a promising abil- ity to support the creation of NLG benchmarks (Gardent et al., 2017). However, English is the only language which has been widely targeted. Even though there are studies which explore the generation of content in languages other than English, to the best of our knowledge, no work has been proposed to generate texts in Brazilian Portuguese from RDF data. In this paper, we propose RDF2PT, a rule-based approach to verbalize RDF data to Brazilian Portuguese. While the exciting avenue of using deep learning techniques in NLG approaches (Gatt and Krahmer, 2017) is open to this task and deep learning has already shown promising results for RDF data (Sleimi and Gardent, 2016), the morphological richness of Portuguese led us to develop a rule-based ap- proach. This was to ensure that we could identify the chal- lenges imposed by this language from the SW perspective before applying Machine Learning (ML) algorithms. RDF2PT is able to generate either a single sentence or a summary of a given resource. In order to validate our approach, …

Content truncated to 500 words