Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Park, Serim"'
Autor:
Zhang, Xinyang, Malkov, Yury, Florez, Omar, Park, Serim, McWilliams, Brian, Han, Jiawei, El-Kishky, Ahmed
Pre-trained language models (PLMs) are fundamental for natural language processing applications. Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagem
Externí odkaz:
http://arxiv.org/abs/2209.07562
Autor:
El-Kishky, Ahmed, Markovich, Thomas, Park, Serim, Verma, Chetan, Kim, Baekjin, Eskander, Ramy, Malkov, Yury, Portman, Frank, Samaniego, Sofía, Xiao, Ying, Haghighi, Aria
Publikováno v:
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2022)
Social networks, such as Twitter, form a heterogeneous information network (HIN) where nodes represent domain entities (e.g., user, content, advertiser, etc.) and edges represent one of many entity interactions (e.g, a user re-sharing content or "fol
Externí odkaz:
http://arxiv.org/abs/2202.05387
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
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Nichols, Jonathan M., Watnik, Abbie T., Doster, Timothy, Park, Serim, Kanaev, Andrey, Cattell, Liam, Rohde, Gustavo K.
We describe a new model for image propagation through open air in the presence of changes in the index of refraction (e.g. due to turbulence) using the theory of optimal transport. We describe the relationship between photon density, or image intensi
Externí odkaz:
http://arxiv.org/abs/1705.01050
Autor:
Park, Sohong, Kim, Duhyeon, Kim, Seonghui, Choi, Gibeom, Yoo, Hodeung, Park, Serim, Cho, Suengmok
Publikováno v:
Foods; Oct2024, Vol. 13 Issue 20, p3287, 16p
Transport based distances, such as the Wasserstein distance and earth mover's distance, have been shown to be an effective tool in signal and image analysis. The success of transport based distances is in part due to their Lagrangian nature which all
Externí odkaz:
http://arxiv.org/abs/1609.08669
Transport-based techniques for signal and data analysis have received increased attention recently. Given their abilities to provide accurate generative models for signal intensities and other data distributions, they have been used in a variety of a
Externí odkaz:
http://arxiv.org/abs/1609.04767
Autor:
Zhang, Xinyang, Malkov, Yury, Florez, Omar, Park, Serim, McWilliams, Brian, Han, Jiawei, El-Kishky, Ahmed
We present TwHIN-BERT, a multilingual language model trained on in-domain data from the popular social network Twitter. TwHIN-BERT differs from prior pre-trained language models as it is trained with not only text-based self-supervision, but also wit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0c47d884fa547e872758c7ca69ac0e5
http://arxiv.org/abs/2209.07562
http://arxiv.org/abs/2209.07562
Autor:
Tan, Fei, Hu, Changwei, Hu, Yifan, Yen, Kevin, Wei, Zhi, Pappu, Aasish, Park, Serim, Li, Keqian
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems; October 2023, Vol. 34 Issue: 10 p7014-7023, 10p