1.1k citations · 1.5k across the 38 of their papers we have counts for
7 papers · 1 filter
Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding
Shiyang Li, Semih Yavuz, Wenhu Chen +1
Task-adaptive pre-training (TAPT) and Self-training (ST) have emerged as the major semi-supervised approaches to improve natural language understanding (NLU) tasks with massive amo…
Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
Ning Ma, Jiajun Bu, Lixian Lu +4
Domain Adaptation has been widely used to deal with the distribution shift in vision, language, multimedia etc. Most domain adaptation methods learn domain-invariant features with…
Lifelong Learning of Hate Speech Classification on Social Media
Jing Qian, Hong Wang, Mai ElSherief +1
Existing work on automated hate speech classification assumes that the dataset is fixed and the classes are pre-defined. However, the amount of data in social media increases every…
Inductive Relation Prediction by BERT
Hanwen Zha, Zhiyu Chen, Xifeng Yan
Relation prediction in knowledge graphs is dominated by embedding based methods which mainly focus on the transductive setting. Unfortunately, they are not able to handle inductive…
Cross-modal Image Retrieval with Deep Mutual Information Maximization
Chunbin Gu, Jiajun Bu, Xixi Zhou +4
In this paper, we study the cross-modal image retrieval, where the inputs contain a source image plus some text that describes certain modifications to this image and the desired i…
Composite Re-Ranking for Efficient Document Search with BERT
Yingrui Yang, Yifan Qiao, Jinjin Shao +3
Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ran…