Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Ahmed El-Kishky"'
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783031333798
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc271746ddf1fcdc8c98a99bb6750c4d
https://doi.org/10.1007/978-3-031-33380-4_29
https://doi.org/10.1007/978-3-031-33380-4_29
Publikováno v:
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::78254ab186329fb9de1885f34b412be7
https://doi.org/10.1145/3534678.3542598
https://doi.org/10.1145/3534678.3542598
A key challenge in social network analysis is understanding the position, or stance, of people in the graph on a large set of topics. While past work has modeled (dis)agreement in social networks using signed graphs, these approaches have not modeled
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::847f591bdbea596d4502ff1d8e9e5379
http://arxiv.org/abs/2201.11675
http://arxiv.org/abs/2201.11675
Autor:
Yuqing Tang, Chang Xu, Benjamin I. P. Rubinstein, Jun Wang, Ahmed El-Kishky, Francisco Guzmán, Trevor Cohn
Publikováno v:
ACL/IJCNLP (Findings)
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a malicious adver
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5e75d27c7ebf2fa1381ae0c6045b9ee
http://arxiv.org/abs/2107.05243
http://arxiv.org/abs/2107.05243
Autor:
Francisco Guzmán, Yi-Lin Tuan, Lucia Specia, Vishrav Chaudhary, Ahmed El-Kishky, Adithya Renduchintala
Publikováno v:
EACL
Quality estimation aims to measure the quality of translated content without access to a reference translation. This is crucial for machine translation systems in real-world scenarios where high-quality translation is needed. While many approaches ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9935ddf0966987919570fb68f81b2fed
http://arxiv.org/abs/2102.04020
http://arxiv.org/abs/2102.04020
Autor:
Francisco Guzmán, Ahmed El-Kishky, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn, Chang Xu
Publikováno v:
ACL/IJCNLP (Findings)
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation. In this work we develop comprehensive assessments of the robustness of neural machine translation systems to numerical text via behav
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c721813f0b7c4e7309d22c0728c0d1a6
Autor:
Francisco Guzmán, Mona Diab, Ahmed El-Kishky, Philipp Koehn, Pascale Fung, Vishrav Chaudhary, Adithya Renduchintala, Wei-Jen Ko, Naman Goyal
Publikováno v:
ACL/IJCNLP (1)
The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these relat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f454fecd833513a1121ba2c6cd2ab066
Cross-lingual named-entity lexica are an important resource to multilingual NLP tasks such as machine translation and cross-lingual wikification. While knowledge bases contain a large number of entities in high-resource languages such as English and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::55c02cb590c7b5daa5daf425eaf5f621
Publikováno v:
SIGIR
While the World Wide Web provides a large amount of text in many languages, cross-lingual parallel data is more difficult to obtain. Despite its scarcity, this parallel cross-lingual data plays a crucial role in a variety of tasks in natural language
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ddcbe5ff2af7e37a3e707550dc5f2d0
https://doi.org/10.1145/3397271.3401417
https://doi.org/10.1145/3397271.3401417
Publikováno v:
WACV
Current semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining. We propose a novel segmentation model that injects visual priors into semantic segm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6a041f7a3e8fdaf06559e213ee40724
https://doi.org/10.1109/wacv45572.2020.9093453
https://doi.org/10.1109/wacv45572.2020.9093453