• Publications
  • Influence
Collective entity linking in web text: a graph-based method
Experimental results show that the proposed graph-based collective EL method can achieve significant performance improvement over the traditional EL methods, and the purely collective nature of the inference algorithm, in which evidence for related EL decisions can be reinforced into high-probability decisions.
Dynamic open spectrum sharing MAC protocol for wireless ad hoc networks
  • L. Ma, Xianpei Han, C.-C. Shen
  • Computer Science
    First IEEE International Symposium on New…
  • 5 December 2005
The dynamic open spectrum sharing (DOSS) MAC protocol allows nodes to adaptively select an arbitrary spectrum for the incipient communication subject to spectrum availability, and offers real-time dynamic spectrum allocation and high spectrum utilization without relying on any infrastructure.
A Generative Entity-Mention Model for Linking Entities with Knowledge Base
This paper proposes a generative probabilistic model, called entity-mention model, which can leverage heterogenous entity knowledge (including popularity knowledge, name knowledge and context knowledge) for the entity linking task.
CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
The CAIL2018 dataset is introduced, the first large-scale Chinese legal dataset for judgment prediction, which contains more than $2.6 million criminal cases published by the Supreme People's Court of China, which are several times larger than other datasets in existing works on judgment prediction.
Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation
This paper proposes a knowledge-based method, called Structural Semantic Relatedness (SSR), which can enhance the named entity disambiguation by capturing and leveraging the structural semantic knowledge in multiple knowledge sources.
An Entity-Topic Model for Entity Linking
This paper proposes a generative model -- called entity-topic model, to effectively join the above two complementary directions of EL research together and can accurately link all mentions in a document.
Named entity disambiguation by leveraging wikipedia semantic knowledge
A novel similarity measure is proposed to leverage Wikipedia semantic knowledge for disambiguation, which surpasses other knowledge bases by the coverage of concepts, rich semantic information and up-to-date content and has been tested on the standard WePS data sets.
Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks
This paper proposes Anchor-Region Networks (ARNs), a sequence-to-nuggets architecture for nested mention detection which first identifies anchor words of all mentions, and then recognizes the mention boundaries for each anchor word by exploiting regular phrase structures.
Variational Recurrent Neural Machine Translation
A novel variational recurrent neural machine translation model that introduces a series of latent random variables to model the translation procedure of a sentence in a generative way, instead of a single latent variable.
Accurate Text-Enhanced Knowledge Graph Representation Learning
This work proposes an accurate text-enhanced knowledge graph representation learning method, which can represent a relation/entity with different representations in different triples by exploiting additional textual information.