The Combination of BERT and Data Oversampling for Answer Type Prediction

Thang Ta Hoang, Olumide Ebenezer Ojo, Olaronke Oluwayemisi Adebanji, Hiram Calvo, Alexander Gelbukh

Producción científica: Contribución a una revistaArtículo de la conferenciarevisión exhaustiva

1 Cita (Scopus)

Resumen

In this paper, we address the Task 1 (of the SMART Task 2021) of predicting the answer categories and types based on target ontologies, which could be useful in knowledge-based Question Answering (QA) systems. We introduced our method by combining the power of BERT architectures with data oversampling via replacements of linked terms to Wikidata and dependent noun phrases to attain the state-of-the-art performance. The accuracy on the DBpedia dataset is 98.5%, whereas NDCG@5 and NDCG@10 are 72.7% and 66.4% respectively. Our model has the best performance compared to other teams, with the accuracy score of 98% and Mean Reciprocal Rank (MRR) of 70% on the Wikidata dataset.

Idioma originalInglés
PublicaciónCEUR Workshop Proceedings
Volumen3119
EstadoPublicada - 2022
Evento2nd SeMantic Answer Type and Relation Prediction Task at ISWC Semantic Web Challenge, SMART 2021 - Virtual, Online
Duración: 26 oct. 2021 → …

Huella

Profundice en los temas de investigación de 'The Combination of BERT and Data Oversampling for Answer Type Prediction'. En conjunto forman una huella única.

Citar esto