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%.
CITATION STYLE
Liu, X., Li, K., Han, B., Zhou, M., Jiang, L., Tse, D., & Xiong, Z. (2010). Collective semantic role labeling on open news corpus by leveraging redundancy. In Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference (Vol. 2, pp. 725–729).
Mendeley helps you to discover research relevant for your work.