Collective Semantic Role Labeling on Open News Corpus by Leveraging Redundancy

  • Liu X
  • Li K
  • Han B
 et al. 
  • 19


    Mendeley users who have this article in their library.
  • 3


    Citations of this article.


We propose a novel MLN-based method that collectively conducts SRL on groups of news sentences. Our method is built upon a baseline SRL, which uses no parsers and leverages redundancy. We evaluate our method on a manually labeled news corpus and demonstrate that news redundancy significantly improves the performance of the baseline, e.g., it improves the F-score from 64.13% to 67.66%. *

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

  • SGR: 80053408716
  • SCOPUS: 2-s2.0-80053408716
  • PUI: 362669989


  • Xiaohua Liu

  • Kuan Li

  • Bo Han

  • Ming Zhou

  • Long Jiang

  • Daniel Tse

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free