Frederico Belcavello- PhD in Linguistics
- Researcher at Universidade Federal de Juiz de Fora
Frederico Belcavello
- PhD in Linguistics
- Researcher at Universidade Federal de Juiz de Fora
Researcher at FrameNet Brasil | UFJF
About
17
Publications
1,778
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
23
Citations
Introduction
Researcher at FrameNet Brasil Lab. Visiting Researcher at Case Western Reserve University. PhD in Linguistics at UFJF - Federal University of Juiz de Fora. Professor at UniAcademia - Centro Universitário Academia.
Current institution
Additional affiliations
August 2024 - present
February 2008 - present
Centro Universitário Academia
Position
- Professor
Education
March 2018 - June 2023
March 2008 - July 2010
Publications
Publications (17)
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...
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...
Multimodal analyses have been growing in importance for several approaches to both Cognitive Linguistics and Natural Language Understanding. Multimodal corpora have been annotated for correlations involving mainly gesture communication and text data and computational infrastructure for dealing with large multimodal corpora have been under developme...
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...
In this research paper, we examine the semantics-pragmatics continuum through a multimodal lens. We propose a new framework that integrates insights from Cognitive Linguistics and Neurolinguistics to advance theoretical and empirical research in Cognitive Neuropragmatics. Language is conceptualized as a dynamic system balancing conventional semanti...
This paper presents a methodology combining multimodal semantic analysis with an eye-tracking experimental protocol to investigate the cognitive effort involved in understanding the communication of future scenarios. To demonstrate the methodology, we conduct a pilot study examining how visual fixation patterns vary during the evaluation of valence...
Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with imag...
This paper presents the Frame 2 dataset, a multimodal dataset built from a corpus of a Brazilian travel TV show annotated for FrameNet categories for both the text and image communicative modes. Frame 2 comprises 230 minutes of video, which are correlated with 2,915 sentences either transcribing the audio spoken during the episodes or the subtitlin...
Este artigo tem como objetivo apresentar uma aplicação do modelo semântico-computacional da FrameNet Brasil (FN-Br) à representação semântica de objetos multimodais. Para tanto, descreve as etapas envolvidas na criação de uma subparte do Dataset da ReINVenTA, com foco na anotação semântica da série de TV Pedro pelo Mundo para as modalidades de text...
Public data systems gather a series of different information about Brazilian citizens. Such information is inserted in the system both via the selection of parameterized options and via open text fields. In this paper we describe the effort of modeling semantic frames for the lexicon of the healthcare domain as a means of tagging the open text fiel...
Public data systems gather different information about Brazilian citizens. Such information is inserted in the system both via the selection of parameterized options and via open text fields. In this paper we describe the effort of modeling semantic frames for the lexicon of the healthcare domain as a means of tagging the open text fields in public...
Multimodal analyses have been growing in importance within several approaches to Cognitive Linguistics and applied fields such as Natural Language Understanding. Nonetheless fine-grained semantic representations of multimodal objects are still lacking, especially in terms of integrating areas such as Natural Language Processing and Computer Vision,...
This paper presents Lutma, a collaborative, semi-constrained, tutorial-based tool for contributing frames and lexical units to the Global FrameNet initiative. The tool parameterizes the process of frame creation, avoiding consistency violations and promoting the integration of frames contributed by the community with existing frames. Lutma is struc...
This paper presents Charon, a web tool for annotating multimodal corpora with FrameNet categories. Annotation can be made for corpora containing both static images and video sequences paired - or not - with text sequences. The pipeline features, besides the annotation interface, corpus import and pre-processing tools.
This paper argues in favor of the adoption of annotation practices for multimodal datasets that recognize and represent the inherently perspectivized nature of multimodal communication. To support our claim, we present a set of annotation experiments in which FrameNet annotation is applied to the Multi30k and the Flickr 30k Entities datasets. We as...
A TV Industrial figurou entre as pioneiras geradoras de programação instaladas fora de uma capital brasileira. Operou em Juiz de Fora entre 1964 e 1979, período no qual foi o único canal caracterizado como emissora local. Esta Dissertação resgata a história da TV Industrial (e seus antecedentes) e analisa o papel mediador desempenhado pela emissora...
Resumo Atualmente, a população urbana tem acesso aos mais diversos tipos de estímulos e informações, estão cercados de soluções às suas indagações. Mas assim como há a divisão entre morro e asfalto para dividir a favela e a "cidade", há uma outra oposição ainda mais antiga entre urbano e rural. A população rural encontra-se distanciada das principa...
