Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Alireza Mohammadshahi"'
Autor:
Alireza Mohammadshahi, James Henderson
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 120-138 (2021)
AbstractWe propose the Recursive Non-autoregressive Graph-to-Graph Transformer architecture (RNGTr) for the iterative refinement of arbitrary graphs through the recursive application of a non-autoregressive Graph-to-Graph Transformer and apply it to
Externí odkaz:
https://doaj.org/article/0c9d604390b84b32854b214228cb85c3
Publikováno v:
Barry, James ORCID: 0000-0003-3051-585X , Mohammadshahi, Alireza, Wagner, Joachim ORCID: 0000-0002-8290-3849 , Foster, Jennifer ORCID: 0000-0002-7789-4853 and Henderson, James ORCID: 0000-0003-3714-4799 (2021) The DCU-EPFL enhanced dependency parser at the IWPT 2021 shared task. In: 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021), 6 August 2021, Online.
We describe the DCU-EPFL submission to the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies. The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilitative towa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33bcbef0dde6f1ad40bfbf0dcefe42b5
http://arxiv.org/abs/2107.01982
http://arxiv.org/abs/2107.01982
Autor:
James Henderson, Alireza Mohammadshahi
Publikováno v:
EMNLP (Findings)
We propose the Graph2Graph Transformer architecture for conditioning on and predicting arbitrary graphs, and apply it to the challenging task of transition-based dependency parsing. After proposing two novel Transformer models of transition-based dep
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e08371609b7a1c0d48ef22084a7656d4
http://arxiv.org/abs/1911.03561
http://arxiv.org/abs/1911.03561
Publikováno v:
LANTERN@EMNLP-IJCNLP
In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3eb92fc35dd33453a61f1a37997e2a9
https://doi.org/10.18653/v1/d19-6605
https://doi.org/10.18653/v1/d19-6605
Autor:
Alireza Mohammadshahi, James Henderson
We propose the Recursive Non-autoregressive Graph-to-Graph Transformer architecture (RNGTr) for the iterative refinement of arbitrary graphs through the recursive application of a non-autoregressive Graph-to-Graph Transformer and apply it to syntacti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::555eedd7879448536f2e819b5256a1aa
https://infoscience.epfl.ch/record/277107
https://infoscience.epfl.ch/record/277107
Autor:
Shvets, Alexander1 (AUTHOR), Wanner, Leo2 (AUTHOR) leo.wanner@upf.edu
Publikováno v:
Mathematics (2227-7390). Oct2022, Vol. 10 Issue 20, p3831-N.PAG. 21p.
With the increasing use of AI in high-stakes domains such as medicine, law, and defense, organizations spend a lot of time and money to make ML models trustworthy. Many books on the subject offer deep dives into theories and concepts. This guide prov