Bootstrapping a Data-Set and Model for Question-Answering in Portuguese (Short Paper)
| Autor: | Carvalho, Nuno Ramos, Simões, Alberto, Almeida, José João |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: | |
| DOI: | 10.4230/oasics.slate.2021.18 |
| Popis: | Question answering systems are mainly concerned with fulfilling an information query written in natural language, given a collection of documents with relevant information. They are key elements in many popular application systems as personal assistants, chat-bots, or even FAQ-based online support systems. This paper describes an exploratory work carried out to come up with a state-of-the-art model for question-answering tasks, for the Portuguese language, based on deep neural networks. We also describe the automatic construction of a data-set for training and testing the model. The final model is not trained in any specific topic or context, and is able to handle generic documents, achieving 50% accuracy in the testing data-set. While the results are not exceptional, this work can support further development in the area, as both the data-set and model are publicly available. OASIcs, Vol. 94, 10th Symposium on Languages, Applications and Technologies (SLATE 2021), pages 18:1-18:5 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|