• Publications
  • Influence
Examining Gender Bias in Languages with Grammatical Gender
TLDR
In this paper, we propose new metrics for evaluating gender bias in word embeddings of gendered languages and further demonstrate evidence ofgender bias in bilingual embeddINGS which align these languages with English. Expand
  • 27
  • 4
  • PDF
Embedding Uncertain Knowledge Graphs
TLDR
We propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space. Expand
  • 21
  • 3
  • PDF
Energy- and spectrum-efficiency tradeoff in OFDM-based cognitive radio systems
TLDR
In this paper, we investigate the Energy Efficiency (EE) - Spectrum Efficiency (SE) tradeoff issue in an OFDM-based cognitive radio (CR) network, where we try to maximize the EE and the SE simultaneously. Expand
  • 13
  • 1
  • PDF
Retrofitting Contextualized Word Embeddings with Paraphrases
TLDR
We propose a simple and effective paraphrase-aware retrofitting (PAR) method that is applicable to arbitrary pretrained contextualized embeddings. Expand
  • 9
  • 1
  • PDF
Energy-Efficient Resource Management in OFDM-Based Cognitive Radio Networks Under Channel Uncertainty
TLDR
In this paper, we investigate the energy consumption issue in cognitive radio (CR) networks while considering practical restrictions, including the power budget of the system. Expand
  • 59
  • PDF
An Optimum-Frequency Tracking Scheme for Ultrasonic Motor
TLDR
This paper presents a high-efficiency optimum frequency tracking scheme with the ability to control the velocity for the ultrasonic motor. Expand
  • 15
Compiling Neural Networks into Tractable Boolean Circuits
We show how to exploit tools and methods from the knowledge compilation literature in order to explain the behavior and verify the properties of neural networks. In particular, we show how to compileExpand
  • 10
Energy-efficient resource allocation in cognitive radio systems
  • Weijia Shi, S. Wang
  • Computer Science
  • IEEE Wireless Communications and Networking…
  • 7 April 2013
TLDR
In this paper, we investigate the energy consumption issue of Cognitive Radio (CR) systems. Expand
  • 15
  • PDF
Interference mitigation and resource allocation in cognitive radio-enabled heterogeneous networks
TLDR
In this paper, we propose an effective interference mitigation scheme to address the resource allocation problem in Heterogeneous networks (HetNets), where cognitive radio technology are employed to identify physical resource blocks (PRBs) that cause light interference to users served by the macrocell. Expand
  • 8
  • PDF
On Tractable Representations of Binary Neural Networks
TLDR
We propose a knowledge compilation approach for explaining and verifying the behavior of a neural network clas- 1It is now recognized that opacity, or lack of explainability is “one of the biggest obstacles to widespread adoption of artificial intelligence”. Expand
  • 8
  • PDF
...
1
2
...