Generalized Inference with Multiple Semantic Role Labeling Systems Shared Task Paper


Authors:

Abstract:

We present an approach to semantic role labeling (SRL) that takes the output of multiple argument classifiers and combines them into a coherent predicateargument output by solving an optimization problem. The optimization stage, which is solved via integer linear programming, takes into account both the recommendation of the classifiers and a set of problem specific constraints, and is thus used both to clean the classification results and to ensure structural integrity of the final role labeling. We illustrate a significant improvement in overall SRL performance through this inference.

Citation:

P. Koomen and V. Punyakanok and D. Roth and W. Yih, Generalized Inference with Multiple Semantic Role Labeling Systems Shared Task Paper. CoNLL  (2005) pp. 181-184

Bibitem:

@inproceedings{KPRY05,
  author = {P. Koomen and V. Punyakanok and D. Roth and W. Yih},
  title = {Generalized Inference with Multiple Semantic Role Labeling Systems Shared Task Paper},
  booktitle = {CoNLL},
  pages = {181-184},
  year = {2005},
  editor = {Ido Dagan and Dan Gildea},
  url = " http://cogcomp.cs.illinois.edu/papers/PunyakanokRoYi05a.pdf",
  funding = {MURI,KINDLE,CLUSTER,XPRESSMP},
  projects = {SM,KINDLE,SRL},
  comment = {Semantic Parsing; joint inference; integer linear programming; combining SRL systems via joint inference; Top system in CoNLL shared task},
}

Projects: