Zobrazeno 1 - 10
of 141
pro vyhledávání: '"Adrian Ulges"'
Autor:
Nosheen Abid, Muhammad Shahzad, Muhammad Imran Malik, Ulrich Schwanecke, Adrian Ulges, György Kovács, Faisal Shafait
Publikováno v:
International Journal of Applied Earth Observations and Geoinformation, Vol 105, Iss , Pp 102568- (2021)
This paper presents a Convolutional Neural Networks (CNN) based Unsupervised Curriculum Learning approach for the recognition of water bodies to overcome the stated challenges for remote sensing based RGB imagery. The unsupervised nature of the prese
Externí odkaz:
https://doaj.org/article/2289ed5a0c7943b5b4a69dff804b8afa
Publikováno v:
IJCNN
We suggest two approaches to incorporate syntactic information into transformer models encoding trees (e.g. abstract syntax trees) and generating sequences. First, we use self-attention with relative position representations to consider structural re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::635fceddb443bead034d4a22eb5c9192
https://doi.org/10.1109/ijcnn52387.2021.9533717
https://doi.org/10.1109/ijcnn52387.2021.9533717
Autor:
Ulrich Schwanecke, Ahmad Salman, Ajmal Mian, Khawar Khurshid, Mark R. Shortis, Shoaib Ahmad Siddiqui, Faisal Shafait, Adrian Ulges
Publikováno v:
ICES Journal of Marine Science. 77:1295-1307
It is interesting to develop effective fish sampling techniques using underwater videos and image processing to automatically estimate and consequently monitor the fish biomass and assemblage in water bodies. Such approaches should be robust against
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5e9415b120e0994e2c65c7f94dadece
https://doi.org/10.1093/icesjms/fsz025
https://doi.org/10.1093/icesjms/fsz025
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030794620
IEA/AIE (2)
IEA/AIE (2)
The construction and completion of knowledge graphs in industrial settings has gained traction over the past years. However, modelling a specific domain is often entailed with significant cost. This can be alleviated by including other knowledge sour
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0baa99a62a08f95551f2a2091e3e476f
https://doi.org/10.1007/978-3-030-79463-7_21
https://doi.org/10.1007/978-3-030-79463-7_21
Publikováno v:
Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021).
We introduce CONTEST, a benchmark for NLP-based unit test completion, the task of predicting a test’s assert statements given its setup and focal method, i.e. the method to be tested. ConTest is large-scale (with 365k datapoints). Besides the test
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::493fa2c8b8753d68e70c59772e057f3e
https://doi.org/10.18653/v1/2021.nlp4prog-1.2
https://doi.org/10.18653/v1/2021.nlp4prog-1.2
Autor:
Markus Eberts, Adrian Ulges
Publikováno v:
EACL
We present a joint model for entity-level relation extraction from documents. In contrast to other approaches - which focus on local intra-sentence mention pairs and thus require annotations on mention level - our model operates on entity level. To d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e8c58afe7b962724863bf53c5e4678f
https://doi.org/10.18653/v1/2021.eacl-main.319
https://doi.org/10.18653/v1/2021.eacl-main.319
Autor:
Nosheen Abid, Muhammad Imran Malik, György Kovács, Faisal Shafait, Ulrich Schwanecke, Adrian Ulges, Muhammad Shahzad
This paper presents a Convolutional Neural Networks (CNN) based Unsupervised Curriculum Learning approach for the recognition of water bodies to overcome the stated challenges for remote sensing based RGB imagery. The unsupervised nature of the prese
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44d280ca56e5969a5e39335529df981c
https://mediatum.ub.tum.de/1659015
https://mediatum.ub.tum.de/1659015
Publikováno v:
SDS
Entity linking, the task of mapping textual mentions to known entities, has recently been tackled using contextualized neural networks. We address the question whether these results -- reported for large, high-quality datasets such as Wikipedia -- tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbd2b4f69652c7716d36c833d5524057
https://doi.org/10.1109/sds49233.2020.00014
https://doi.org/10.1109/sds49233.2020.00014
Publikováno v:
COLING
We introduce ManyEnt, a benchmark for entity typing models in few-shot scenarios. ManyEnt offers a rich typeset, with a fine-grain variant featuring 256 entity types and a coarse-grain one with 53 entity types. Both versions have been derived from th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::22821170fbe4a1ad288cabe1e95147c6
https://doi.org/10.18653/v1/2020.coling-main.486
https://doi.org/10.18653/v1/2020.coling-main.486
Publikováno v:
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs).
We propose an open-world knowledge graph completion model that can be combined with common closed-world approaches (such as ComplEx) and enhance them to exploit text-based representations for entities unseen in training. Our model learns relation-spe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f3ff0ac6927672eddc71fd835bfb5e0
https://doi.org/10.18653/v1/2020.textgraphs-1.9
https://doi.org/10.18653/v1/2020.textgraphs-1.9