Cookies
Usamos cookies para melhorar nosso site e a sua experiência. Ao continuar a navegar no site, você aceita a nossa política de cookies. Ver mais
Aceitar Rejeitar
  • Menu
Sobre
Download foto HD

Sobre

Ricardo Campos é professor adjunto da Unidade Departamental de Tecnologias de Informação e Comunicação do Instituto Politécnico de Tomar [http://www.ipt.pt] e Professor convidado do Porto Business School [http://www.pbs.up.pt]. É investigador integrado do LIAAD-INESC TEC [https://www.inesctec.pt/pt/centros/liaad], Laboratório de Inteligência Artificial e Apoio à Decisão da Universidade do Porto, e colaborador do Ci2 [http://www.ci2.ipt.pt/], o Centro de Investigação em Cidades Inteligentes do Instituto Politécnico de Tomar.

Possui um doutoramento em Ciência dos Computadores pela Universidade do Porto (UP). Em 2013, foi premiado pela Fraunhofer Portugal Challenge 2013 como a melhor tese de doutoramento a concurso e distinguido como investigador “fora-de-série” pelo INESC TEC, em virtude da sua investigação em pesquisa de informação temporal.

Possui mais de 10 anos de experiência de investigação nas áreas de recuperação de informação e processamento da linguagem natural. Em 2018 foi-lhe atribuído o best short paper award na 40th International Conference on Information Retrieval (ECIR’18) pelo paper intitulado “A Text Feature Based Automatic Keyword Extraction Method for Single Documents” [http://yake.inesctec.pt]. No mesmo ano foi premiado pelo Arquivo.pt como o vencedor dos Prémios Arquivo.pt 2018 pelo projeto Conta-me Histórias [http://contamehistorias.pt]. Em 2019 viu-lhe ser atribuído o Best Demo Presentation Award na 41st International Conference on Information Retrieval (ECIR’19) pelo paper intitulado “Interactive System for Automatically Generating Temporal Narratives” [http://tellmestories.pt]. Na mesma conferência foi-lhe atribuído o Recognized Reviewer Award pelos seus reviews enquanto membro do Program Committee do ECIR’19. Em 2019 foi também nomeado outstanding reviewer na conferência NAACL-HTL'19.

Co-organizou conferências e workshops internacionais na área da pesquisa de informação, e é regularmente membro do comité científico de várias conferências internacionais. É também membro do editorial board do Information Processing and Management Journal. Para mais informações consultar por favor http://www.ccc.ipt.pt/~ricardo

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Ricardo Campos
  • Cluster

    Informática
  • Cargo

    Investigador Sénior
  • Desde

    01 julho 2012
001
Publicações

2020

YAKE! Keyword extraction from single documents using multiple local features

Autores
Campos, R; Mangaravite, V; Pasquali, A; Jorge, A; Nunes, C; Jatowt, A;

Publicação
Information Sciences

Abstract
As the amount of generated information grows, reading and summarizing texts of large collections turns into a challenging task. Many documents do not come with descriptive terms, thus requiring humans to generate keywords on-the-fly. The need to automate this kind of task demands the development of keyword extraction systems with the ability to automatically identify keywords within the text. One approach is to resort to machine-learning algorithms. These, however, depend on large annotated text corpora, which are not always available. An alternative solution is to consider an unsupervised approach. In this article, we describe YAKE!, a light-weight unsupervised automatic keyword extraction method which rests on statistical text features extracted from single documents to select the most relevant keywords of a text. Our system does not need to be trained on a particular set of documents, nor does it depend on dictionaries, external corpora, text size, language, or domain. To demonstrate the merits and significance of YAKE!, we compare it against ten state-of-the-art unsupervised approaches and one supervised method. Experimental results carried out on top of twenty datasets show that YAKE! significantly outperforms other unsupervised methods on texts of different sizes, languages, and domains. © 2019 Elsevier Inc.

2020

The 3$$^{\mathrm {rd}}$$ International Workshop on Narrative Extraction from Texts: Text2Story 2020

Autores
Campos, R; Jorge, A; Jatowt, A; Bhatia, S;

Publicação
Lecture Notes in Computer Science - Advances in Information Retrieval

Abstract

2020

Proceedings of Text2Story - Third Workshop on Narrative Extraction From Texts co-located with 42nd European Conference on Information Retrieval, Text2Story@ECIR 2020, Lisbon, Portugal, April 14th, 2020 [online only]

Autores
Campos, R; Jorge, AM; Jatowt, A; Bhatia, S;

Publicação
Text2Story@ECIR

Abstract

2020

Event-Related Query Classification with Deep Neural Networks

Autores
Gandhi, S; Mansouri, B; Campos, R; Jatowt, A;

Publicação
The Web Conference 2020 - Companion of the World Wide Web Conference, WWW 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. © 2020 ACM.

2020

Joint event extraction along shortest dependency paths using graph convolutional networks

Autores
Balali, A; Asadpour, M; Campos, R; Jatowt, A;

Publicação
Knowledge-Based Systems

Abstract