Zobrazeno 1 - 10
of 91
pro vyhledávání: '"Yen, Kevin"'
While a multitude of studies have been conducted on graph drawing, many existing methods only focus on optimizing a single aesthetic aspect of graph layouts, which can lead to sub-optimal results. There are a few existing methods that have attempted
Externí odkaz:
http://arxiv.org/abs/2206.06434
We proposes a novel algorithm, ANTHRO, that inductively extracts over 600K human-written text perturbations in the wild and leverages them for realistic adversarial attack. Unlike existing character-based attacks which often deductively hypothesize a
Externí odkaz:
http://arxiv.org/abs/2203.10346
Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed. In this work, we explore an alternative perspective by augmenting reactiv
Externí odkaz:
http://arxiv.org/abs/2109.08805
Coming up with effective ad text is a time consuming process, and particularly challenging for small businesses with limited advertising experience. When an inexperienced advertiser onboards with a poorly written ad text, the ad platform has the oppo
Externí odkaz:
http://arxiv.org/abs/2108.08226
In the past decades, many graph drawing techniques have been proposed for generating aesthetically pleasing graph layouts. However, it remains a challenging task since different layout methods tend to highlight different characteristics of the graphs
Externí odkaz:
http://arxiv.org/abs/2106.15347
Autor:
Qin, Xuan, Liu, Meizhu, Hu, Yifan, Moo, Christina, Riblet, Christian M., Hu, Changwei, Yen, Kevin, Ling, Haibin
In this paper, we propose a method that efficiently utilizes appearance features and text vectors to accurately classify political posters from other similar political images. The majority of this work focuses on political posters that are designed t
Externí odkaz:
http://arxiv.org/abs/2012.10728
Publikováno v:
EMNLP 2020
We present our HABERTOR model for detecting hatespeech in large scale user-generated content. Inspired by the recent success of the BERT model, we propose several modifications to BERT to enhance the performance on the downstream hatespeech classific
Externí odkaz:
http://arxiv.org/abs/2010.08865
Autor:
Lee, Soojin, Rieu, ZunHyan, Kim, Regina EY, Lee, Minho, Yen, Kevin, Yong, Junghyun, Kim, Donghyeon
Publikováno v:
In Brain Research Bulletin December 2023 205
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Gholami, Mohsen, Ward, Rabab, Mahal, Ravneet, Mirian, Maryam, Yen, Kevin, Park, Kye Won, McKeown, Martin J., Wang, Z. Jane
Publikováno v:
In Medical Image Analysis October 2023 89