PLSUM: Generating PT-BR Wikipedia by Summarizing Multiple Websites
This work addresses the expansion of Brazilian Portuguese Wikipedia, an incremental improvement for users seeking intelligible knowledge in that language.
The authors tackled the lack of descriptions in Brazilian Portuguese Wikipedia by developing PLSum, a framework that generates wiki-like abstractive summaries from multiple websites, achieving meaningful results as demonstrated through a dataset of thousands of examples.
Wikipedia is an important free source of intelligible knowledge. Despite that, Brazilian Portuguese Wikipedia still lacks descriptions for many subjects. In an effort to expand the Brazilian Wikipedia, we contribute PLSum, a framework for generating wiki-like abstractive summaries from multiple descriptive websites. The framework has an extractive stage followed by an abstractive one. In particular, for the abstractive stage, we fine-tune and compare two recent variations of the Transformer neural network, PTT5, and Longformer. To fine-tune and evaluate the model, we created a dataset with thousands of examples, linking reference websites to Wikipedia. Our results show that it is possible to generate meaningful abstractive summaries from Brazilian Portuguese web content.