Alexandre Diniz da Costa

Alexandre Diniz da Costa
  • Professor (Full) at Universidade Federal de Juiz de Fora

About

7
Publications
888
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
25
Citations
Current institution
Universidade Federal de Juiz de Fora
Current position
  • Professor (Full)

Publications

Publications (7)
Article
Full-text available
In this paper we present a database management and annotation tool for running an enriched FrameNet database, the FrameNet Brasil WebTool. We demonstrate how the entity-based model of such a tool allows for the addition of two types of data-structure to FrameNet Brasil, both of which aimed at refining the granularity of the semantic representations...
Article
Full-text available
Frame Semantics includes context as a central aspect of the theory. Frames themselves can be regarded as a representation of the immediate context against which meaning is to be construed. Moreover, the notion of frame invocation includes context as one possible source of information comprehenders use to construe meaning. As the original implementa...
Preprint
Full-text available
In this paper we present Scylla, a methodology for domain adaptation of Neural Machine Translation (NMT) systems that make use of a multilingual FrameNet enriched with qualia relations as an external knowledge base. Domain adaptation techniques used in NMT usually require fine-tuning and in-domain training data, which may pose difficulties for thos...
Chapter
Full-text available
Multimodal aspects of human communication are key in several applications of Natural Language Processing, such as Machine Translation and Natural Language Generation. Despite recent advances in integrating multimodality into Computational Linguistics, the merge between NLP and Computer Vision techniques is still timid, especially when it comes to p...
Presentation
When people decide to travel, they need information to plan their tourism activities. There is a lot of information available online in several types of semioses, but it is humanly impossible to access and categorize all this information. Based on that, we aim to build a common semantic representation for both textual and imagetic information that...
Article
Full-text available
p class="Default"> Este trabalho apresenta uma proposta para representar computacionalmente construções do Português Brasileiro, no âmbito do Constructicon da FrameNet Brasil. Dessa forma, demonstra de que maneira as teorias irmãs da Semântica de Frames e da Gramática das Construções podem ser implementadas computacionalmente com vias a sustentar a...

Network

Cited By