The Necessity of Syntactic Parsing for Semantic Role Labeling
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1117-1122.
Abstract
We provide an experimental study of the role of syntactic parsing in semantic role labeling. Our conclusions demonstrate that syntactic parse information is clearly most relevant in the very first stage – the pruning stage. In addition, the quality of the pruning stage cannot be determined solely based on its recall and precision. Instead it depends on the characteristics of the output candidates that make downstream problems easier or harder. Motivated by this observation, we suggest an effective and simple approach of combining different semantic role labeling systems through joint inference, which significantly improves the performance.
@inproceedings{ijcai2005p234,
title = {The Necessity of Syntactic Parsing for Semantic Role Labeling},
author = {Punyakanok, Vasin and Roth, Dan and Yih, Wen-tau},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1117--1122},
year = {2005},
url = {https://ijcai.org/proceedings/2005/234},
}
TY - CPAPER TI - The Necessity of Syntactic Parsing for Semantic Role Labeling AU - Punyakanok, Vasin AU - Roth, Dan AU - Yih, Wen-tau T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1117 EP - 1122 UR - https://ijcai.org/proceedings/2005/234 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
