no code implementations • NLPerspectives (LREC) 2022 • Tiago Timponi Torrent, Arthur Lorenzi, Ely Edison da Silva Matos, Frederico Belcavello, Marcelo Viridiano, Maucha Andrade Gamonal
This paper presents Lutma, a collaborative, semi-constrained, tutorial-based tool for contributing frames and lexical units to the Global FrameNet initiative.
no code implementations • NLPerspectives (LREC) 2022 • Marcelo Viridiano, Tiago Timponi Torrent, Oliver Czulo, Arthur Lorenzi Almeida, Ely Edison da Silva Matos, Frederico Belcavello
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.
no code implementations • LREC 2022 • Alexandre Diniz Costa, Mateus Coutinho Marim, Ely Edison da Silva Matos, Tiago Timponi Torrent
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.
no code implementations • LREC 2020 • Frederico Belcavello, Marcelo Viridiano, Alex Diniz da Costa, re, Ely Edison da Silva Matos, Tiago Timponi Torrent
Multimodal aspects of human communication are key in several applications of Natural Language Processing, such as Machine Translation and Natural Language Generation.
no code implementations • RANLP 2019 • Oliver Czulo, Tiago Timponi Torrent, Ely Edison da Silva Matos, Alex Costa, re Diniz da, Debanjana Kar
We propose a metric for machine translation evaluation based on frame semantics which does not require the use of reference translations or human corrections, but is aimed at comparing original and translated output directly.
no code implementations • WS 2017 • Nat{\'a}lia Duarte Mar{\c{c}}{\~a}o, Tiago Timponi Torrent, Ely Edison da Silva Matos