Zobrazeno 1 - 10
of 641
pro vyhledávání: '"graph transduction"'
This paper presents the system used in our submission to the \textit{CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing}. Our system is a graph-based parser which combines an extended pointer-generator network that generates nodes
Externí odkaz:
http://arxiv.org/abs/2004.03849
We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed parser is aligner-free, and it c
Externí odkaz:
http://arxiv.org/abs/1905.08704
Autor:
Vascon, Sebastiano, Aslan, Sinem, Torcinovich, Alessandro, van Laarhoven, Twan, Marchiori, Elena, Pelillo, Marcello
Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain. In this paper, we propose to cast this problem in
Externí odkaz:
http://arxiv.org/abs/1905.02036
Recognizing the type of an ancient coin requires theoretical expertise and years of experience in the field of numismatics. Our goal in this work is automatizing this time consuming and demanding task by a visual classification framework. Specificall
Externí odkaz:
http://arxiv.org/abs/1810.01091
Semi-supervised learning is a popular class of techniques to learn from labeled and unlabeled data. The paper proposes an application of a recently proposed approach of graph transduction that exploits game theoretic notions to the problem of multipl
Externí odkaz:
http://arxiv.org/abs/1806.07227
Publikováno v:
In Information Sciences January 2018 423:187-199
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Erdem, Aykut1 aykut.erdem@hacettepe.edu.tr, Pelillo, Marcello2 pelillo@dsi.unive.it, Dengyong Zhou
Publikováno v:
Neural Computation. Mar2012, Vol. 24 Issue 3, p700-723. 24p. 1 Diagram, 4 Charts, 3 Graphs.
Publikováno v:
Pattern Recognition Letters. 134:96-105
Motivated by the observation that network-based methods for the automatic prediction of protein functions can greatly benefit from exploiting both the similarity between proteins and the similarity between functional classes (as encoded, e.g., in the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc7ebc12cf9a156424bb3ab216f38ac1
https://doi.org/10.1016/j.patrec.2018.04.002
https://doi.org/10.1016/j.patrec.2018.04.002