Quality Flaws Prediction in Wikipedia by Using Deep Learning Approaches
Quality flaws prediction in Wikipedia is an ongoing research trend. In particular, in this work we tackle the problem of automatically predicting four out of the ten most frequent quality flaws; namely: No footnotes, Notability, Primary Sources and Refmprove. Different deep learning state-of-the-art...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Español |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/149435 |
| Aporte de: |
| Sumario: | Quality flaws prediction in Wikipedia is an ongoing research trend. In particular, in this work we tackle the problem of automatically predicting four out of the ten most frequent quality flaws; namely: No footnotes, Notability, Primary Sources and Refmprove. Different deep learning state-of-the-art approaches were evaluated on the test corpus from the 1st International Competition on Quality Flaw Prediction in Wikipedia; a well-known uniform evaluation corpus from this research field. Particularly, the results show that TabNet reachs or improves the existing benchmarks for the Notability and Refmprove flaws, and performs in a very competitive way for the other two remaining flaws. |
|---|