2020
Authors
Lopes, MS; Oliveira, BMPM; Neves, O; Melim, D; Freitas, P; Correia, F;
Publication
PROCEEDINGS OF THE NUTRITION SOCIETY
Abstract
2020
Authors
Are, M; Santos, E; Oliveira, BMPM; Correia, F; Poínhos, R;
Publication
PROCEEDINGS OF THE NUTRITION SOCIETY
Abstract
2020
Authors
Cardoso, F; Azevedo, M; Oliveira, B; Poinhos, R; Carvaho, J; Almeida, R; Correia, F;
Publication
PROCEEDINGS OF THE NUTRITION SOCIETY
Abstract
2020
Authors
Redondo, Ana M.S; Sampaio, Marta.A.; Bruno M P M Oliveira; Pereira, Bárbara; Almeida, Maria Daniel Vaz de; Rocha, Nair; Morais, Cecília;
Publication
Abstract
2020
Authors
Bruno M P M Oliveira; Poínhos, Rui; Sorokina, A.; Afonso, Cláudia; Franchini, Bela; Pereira, Bárbara; Correia, Flora; Fonseca, L.; Sousa, M.; Monteiro, A.; Almeida, Maria Daniel Vaz de;
Publication
Abstract
2020
Authors
Gandhi, S; Mansouri, B; Campos, R; Jatowt, A;
Publication
WWW'20: COMPANION PROCEEDINGS OF THE WEB CONFERENCE 2020
Abstract
Users tend to search over the Internet to get the most updated news when an event occurs. Search engines should then be capable of effectively retrieving relevant documents for event-related queries. As the previous studies have shown, different retrieval models are needed for different types of events. Therefore, the first step for improving effectiveness is identifying the event-related queries and determining their types. In this paper, we propose a novel model based on deep neural networks to classify event-related queries into four categories: periodic, aperiodic, one-time-only, and non-event. The proposed model combines recurrent neural networks (by feeding two LSTM layers with query frequencies) and visual recognition models (by transforming time-series data from a 1D signal to a 2D image - later passed to a CNN model) for effective query type estimation. Worth noting is that our method uses only the time-series data of query frequencies, without the need to resort to any external sources such as contextual data, which makes it language and domain-independent with regards to the query issued. For evaluation, we build upon the previous datasets on event-related queries to create a new dataset that fits the purpose of our experiments. The obtained results show that our proposed model can achieve an F1-score of 0.87.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.