Predicting and Integrating Expected Answer Types into a Simple Recurrent Neural Network Model for Answer Sentence Selection
Título del documento: Predicting and Integrating Expected Answer Types into a Simple Recurrent Neural Network Model for Answer Sentence Selection
Revue: Computación y sistemas
Base de datos:
Número de sistema: 000560448
ISSN: 1405-5546
Autores: 1
1
2
Instituciones: 1Université Paris-Saclay, Orsay, Paris. Francia
2Université Paris sud - Paris XI, Ile de France. Francia
Año:
Periodo: Jul-Sep
Volumen: 23
Número: 3
Paginación: 665-673
País: México
Idioma: Inglés
Tipo de documento: Artículo
Resumen en inglés Since end-to-end deep learning models have started to replace traditional pipeline architectures of question answering systems, features such as expected answertypes which are based on the question semantics are seldom used explicitly in the models. In this paper, we propose a convolution neural network model to predict these answer types based on question words and a recurrent neural network model to find sentence similarity scores between question and answer sentences. The proposed model outperforms the current state of the art results on an answer sentence selection task in open domain question answering by 1.88% on MAP and 2.96% on MRR scores.
Disciplinas: Ciencias de la computación
Palabras clave: Inteligencia artificial
Keyword: Question answering,
Deep learning,
Answer sentence selection,
Expected answer types,
Sentence similarity,
Artificial intelligence
Texte intégral: Texto completo (Ver HTML) Texto completo (Ver PDF)