RDF2PT: Generating Brazilian Portuguese Texts from RDF Data
By Diego Moussallem, Thiago Castro Ferreira, Marcos Zampieri, Maria Cláudia Reis Cavalcanti, Geraldo Bonorino Xexéo, Mariana Neves, Axel-Cyrille Ngonga Ngomo. 2018
14 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Emiel Krahmer
- Thiago Castro Ferreira
- Filip Jurvc'ivcek
- Ondrej Dusek
- Sander Wubben
- Diego Moussallem
- Verena Rieser
- Ehud Reiter
In Natural Language Processing
- Filip Jurvc'ivcek
- Thiago Castro Ferreira
- Emiel Krahmer
- Ondrej Dusek
- Diego Moussallem
- Sander Wubben
- Verena Rieser
- Mihir Kale
Citations in the corpus
- Neural Generation for Czech: Data and Baselines (2019, methodology): “In data-to-text generation, the recent work of Moussallem et al. (2018) is applied to Portuguese, but is largely rule-based.”
- Enriching the WebNLG corpus (2018, background): “In future work, we envision translating the corpus for other morphologically rich languages, as Brazilian Portuguese (Moussallem et al., 2018).”