• Publications
  • Influence
Learning to Generate Questions by LearningWhat not to Generate
TLDR
We propose our Clue Guided Copy Network for Question Generation (CGC-QG), which is a sequence-to-sequence generative model with copying mechanism, yet employing a variety of novel components and techniques to boost the performance of question generation. Expand
  • 27
  • 8
  • PDF
Block SAPOR: block second-order Arnoldi method for passive order reduction of multi-input multi-output RCS interconnect circuits
  • Bang Liu, X. Zeng, +4 authors D. Zhou
  • Computer Science
  • Proceedings of the ASP-DAC . Asia and South…
  • 18 January 2005
TLDR
We propose a Block SAPOR (Block Second-order Arnoldi method for Passive Order Reduction) for multi-input multi-output RCS circuits. Expand
  • 21
  • 8
  • PDF
Growing Story Forest Online from Massive Breaking News
TLDR
We describe our experience of implementing a news content organization system at Tencent that discovers events from vast streams of breaking news and evolves news story structures in an online fashion. Expand
  • 15
  • 3
  • PDF
Network latency prediction for personal devices: Distance-feature decomposition from 3D sampling
TLDR
We propose a distance-feature decomposition algorithm that can decompose latency matrices into a distance component and a network feature component, and further leverage the structured pattern inherent in the 3D sampled data to increase estimation accuracy. Expand
  • 11
  • 2
  • PDF
Matching Long Text Documents via Graph Convolutional Networks
TLDR
We propose the Concept Interaction Graph to yield a graph representation for a document, with vertices representing different concepts, each being one or a group of coherent keywords in the document, and with edges representing the interactions between different concepts. Expand
  • 21
  • 1
  • PDF
PASS: Parking-Lot-Assisted Carpool over Vehicular Ad Hoc Networks
TLDR
We propose PASS: a parking-lot-assisted carpool method over vehicular ad hoc networks (VANETs). Expand
  • 15
  • 1
Matching Natural Language Sentences with Hierarchical Sentence Factorization
TLDR
We propose Hierarchical Sentence Factorization---a technique to factorize a sentence into a hierarchical representation, with the components at each different scale reordered into a "predicate-argument" form. Expand
  • 12
  • 1
  • PDF
Latency reduction and load balancing in coded storage systems
TLDR
We provide a new perspective to load balancing in coded storage systems by proactively and intelligently launching degraded reads and propose a variety of schemes to make optimal decisions either per request or across requests. Expand
  • 8
  • 1
Deep Learning versus Professional Healthcare Equipment: A Fine-Grained Breathing Rate Monitoring Model
TLDR
We propose a deep learning-based fine-grained breathing rate monitoring algorithm that works on smartphone and achieves professional-level accuracy. Expand
  • 7
  • 1
  • PDF
Mobility Crowdsourcing: Toward Zero-Effort Carpooling on Individual Smartphone
TLDR
In current carpooling systems, drivers and passengers offer and search for their trips through available mediums, for example, accessing carpool website by smartphone, for finding a possible match of the journey. Expand
  • 11
  • PDF