Statistical Parsing with Probabilistic Symbol-Refined Tree Substitution Grammars
Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Pages 3082-3085.
Abstract
We present probabilistic Symbol-Refined Tree Substitution Grammars (SR-TSG) for statistical parsing of natural language sentences. An SR-TSG is an extension of the conventional TSG model where each nonterminal symbol can be refined (subcategorized) to fit the training data. Our probabilistic model is consistent based on the hierarchical Pitman-Yor Process to encode backoff smoothing from a fine-grained SR-TSG to simpler CFG rules, thus all grammar rules can be learned from training data in a fully automatic fashion. Our SR-TSG parser achieves the state-of-the-art performance on the Wall Street Journal (WSJ) English Penn Treebank data.
@inproceedings{ijcai2013p461,
title = {Statistical Parsing with Probabilistic Symbol-Refined Tree Substitution Grammars},
author = {Shindo, Hiroyuki and Miyao, Yusuke and Fujino, Akinori and Nagata, Masaaki},
booktitle = {Proceedings of the Twenty-Third International Joint Conference on
Artificial Intelligence, {IJCAI-13}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Francesca Rossi},
pages = {3082--3085},
year = {2013},
month = {8},
url = {https://ijcai.org/proceedings/2013/461},
}
TY - CPAPER TI - Statistical Parsing with Probabilistic Symbol-Refined Tree Substitution Grammars AU - Shindo, Hiroyuki AU - Miyao, Yusuke AU - Fujino, Akinori AU - Nagata, Masaaki T2 - Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI-13 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2013 SP - 3082 EP - 3085 UR - https://ijcai.org/proceedings/2013/461 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
