|
V. Punyakanok, D. Roth, W. Yih
Generalized Inference with
Multiple Semantic Role Labeling Systems
CoNLL-05
shared task
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.
@InProceedings{PunyakanokRoYi05:CoNLL,
author = {V. Punyakanok and D. Roth and W. Yih},
title = {Generalized Inference with Multiple Semantic Role Labeling Systems},
booktitle = {Proc. of the Annual Conference on Computational Natural Language Learning ({CoNLL})},
editor = {Ido Dagan and Dan Gildea},
year = {2005},
pages = {181-184}
} |
