activity
20172021
most citedRepulsive Attention: Rethinking Multi-head Attention as Bayesian Inference

7 citations · 24 across the 8 of their papers we have counts for

collaborators

9 papers

cs.CL20211 cited

BERT-Beta: A Proactive Probabilistic Approach to Text Moderation

Fei Tan, Yifan Hu, Kevin Yen +1

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…

cs.CL20215 cited

TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity

Shaunak Mishra, Changwei Hu, Manisha Verma +3

Coming up with effective ad text is a time consuming process, and particularly challenging for small businesses with limited advertising experience. When an inexperienced advertise…

cs.LG20213 cited

What's in a Name? -- Gender Classification of Names with Character Based Machine Learning Models

Yifan Hu, Changwei Hu, Thanh Tran +3

Gender information is no longer a mandatory input when registering for an account at many leading Internet companies. However, prediction of demographic information such as gender…

cs.CV2020

Political Posters Identification with Appearance-Text Fusion

Xuan Qin, Meizhu Liu, Yifan Hu +5

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…

cs.LG20207 cited

Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference

Bang An, Jie Lyu, Zhenyi Wang +6

The neural attention mechanism plays an important role in many natural language processing applications. In particular, the use of multi-head attention extends single-head attentio…

cs.CL2020

HABERTOR: An Efficient and Effective Deep Hatespeech Detector

Thanh Tran, Yifan Hu, Changwei Hu +4

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…