156 citations
- Carnegie Mellon UniversityUS4 papers
- Massachusetts Institute of TechnologyUS4 papers
- Johns Hopkins UniversityUS3 papers
- Toyota Technological Institute at ChicagoUS3 papers
- University of Maryland, College ParkUS3 papers
- Amazon (United States)US2 papers
- Microsoft Research (United Kingdom)GB2 papers
- Nanyang Technological UniversitySG2 papers
- Rice UniversityUS2 papers
- The University of AdelaideAU2 papers
- University of Illinois ChicagoUS2 papers
- Allen (United States)US1 paper
55 papers · 1 filter
3D-Aided Data Augmentation for Robust Face Understanding
Yifan Xing, Yuanjun Xiong, Wei Xia
Data augmentation has been highly effective in narrowing the data gap and reducing the cost for human annotation, especially for tasks where ground truth labels are difficult and e…
CoLAKE: Contextualized Language and Knowledge Embedding
Tianxiang Sun, Yunfan Shao, Xipeng Qiu +4
With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained…
Improving Device Directedness Classification of Utterances with Semantic Lexical Features
Kellen Gillespie, Ioannis C. Konstantakopoulos, Xingzhi Guo +2
User interactions with personal assistants like Alexa, Google Home and Siri are typically initiated by a wake term or wakeword. Several personal assistants feature "follow-up" mode…
Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study
Saurabh Kulshreshtha, José Luis Redondo-García, Ching-Yun Chang
Multilingual BERT (mBERT) has shown reasonable capability for zero-shot cross-lingual transfer when fine-tuned on downstream tasks. Since mBERT is not pre-trained with explicit cro…
Improve Transformer Models with Better Relative Position Embeddings
Zhiheng Huang, Davis Liang, Peng Xu +1
Transformer architectures rely on explicit position encodings in order to preserve a notion of word order. In this paper, we argue that existing work does not fully utilize positio…
Differentially Private Adversarial Robustness Through Randomized Perturbations
Nan Xu, Oluwaseyi Feyisetan, Abhinav Aggarwal +2
Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictio…