no code implementations • EMNLP 2020 • Fei Tan, Yifan Hu, Changwei Hu, Keqian Li, Kevin Yen
In this work, we present a new language pre-training model TNT (Text Normalization based pre-training of Transformers) for content moderation.
1 code implementation • Medical Image Analysis 2023 • Mohsen Gholami, Rabab Ward, Ravneet Mahal, Maryam Mirian, Kevin Yen, Kye Won Park, Martin J. McKeown, Z. Jane Wang
The method obtained state-of-the-art results on the Human3. 6M dataset.
no code implementations • 13 Jun 2022 • Xiaoqi Wang, Kevin Yen, Yifan Hu, Han-Wei Shen
There are a few existing methods that have attempted to develop a flexible solution for optimizing different aesthetic aspects measured by different aesthetic criteria.
1 code implementation • Findings (ACL) 2022 • Thai Le, Jooyoung Lee, Kevin Yen, Yifan Hu, Dongwon Lee
We find that adversarial texts generated by ANTHRO achieve the best trade-off between (1) attack success rate, (2) semantic preservation of the original text, and (3) stealthiness--i. e. indistinguishable from human writings hence harder to be flagged as suspicious.
no code implementations • EMNLP 2021 • Fei Tan, Yifan Hu, Kevin Yen, Changwei Hu
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.
no code implementations • 18 Aug 2021 • Shaunak Mishra, Changwei Hu, Manisha Verma, Kevin Yen, Yifan Hu, Maxim Sviridenko
To realize this opportunity, we propose an ad text strength indicator (TSI) which: (i) predicts the click-through-rate (CTR) for an input ad text, (ii) fetches similar existing ads to create a neighborhood around the input ad, (iii) and compares the predicted CTRs in the neighborhood to declare whether the input ad is strong or weak.
no code implementations • 27 Jun 2021 • Xiaoqi Wang, Kevin Yen, Yifan Hu, Han-Wei Shen
In this paper, we propose a Convolutional Graph Neural Network based deep learning framework, DeepGD, which can draw arbitrary graphs once trained.
no code implementations • 19 Dec 2020 • Xuan Qin, Meizhu Liu, Yifan Hu, Christina Moo, Christian M. Riblet, Changwei Hu, Kevin Yen, Haibin Ling
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.
no code implementations • EMNLP 2020 • Thanh Tran, Yifan Hu, Changwei Hu, Kevin Yen, Fei Tan, Kyumin Lee, Serim Park
HABERTOR inherits BERT's architecture, but is different in four aspects: (i) it generates its own vocabularies and is pre-trained from the scratch using the largest scale hatespeech dataset; (ii) it consists of Quaternion-based factorized components, resulting in a much smaller number of parameters, faster training and inferencing, as well as less memory usage; (iii) it uses our proposed multi-source ensemble heads with a pooling layer for separate input sources, to further enhance its effectiveness; and (iv) it uses a regularized adversarial training with our proposed fine-grained and adaptive noise magnitude to enhance its robustness.