The necessity of syntactic parsing for semantic role labeling

The necessity of syntactic parsing for semantic role labeling (2005)

Cached

Download Links

[www.ijcai.org]
[l2r.cs.uiuc.edu]

Other Repositories/Bibliography

DBLP

by Vasin Punyakanok , Dan Roth , Wen-tau Yih

Venue:	In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI
Citations:	50 - 15 self

BibTeX

@INPROCEEDINGS{Punyakanok05thenecessity,
    author = {Vasin Punyakanok and Dan Roth and Wen-tau Yih},
    title = {The necessity of syntactic parsing for semantic role labeling},
    booktitle = {In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI},
    year = {2005},
    pages = {1117--1123}
}

Years of Citing Articles

Bookmark

OpenURL

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. 1

Citations

780	Head-Driven Statistical Models for Natural Language Parsing - Collins - 1999
311	Large margin classification using the perceptron algorithm - Freund, Schapire - 1999
164	M: From Treebank to PropBank - Kingsbury, Palmer
154	Learning to resolve natural language ambiguities: A unified approach - Roth - 1998
109	Shallow semantic parsing using support vector machines - Pradhan, Ward, et al. - 2004
90	Using predicate-argument structures for information extraction - Surdeanu, Harabagiu, et al. - 2003
89	Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling - Carreras, rques, et al.
87	Intricacies of Collins’ parsing model - Bikel - 2004
83	The use of classifiers in sequential inference - Punyakanok, Roth - 2001
71	Immediate-head parsing for language models - Charniak - 2001
67	Calibrating features for semantic role labeling - Xue, Palmer - 2004
62	D.: Semantic role labeling via integer linear programming inference - Punyakanok, Roth, et al. - 2004
60	The necessity of parsing for predicate argument recognition - Gildea, Palmer - 2002
47	Probabilistic Reasoning for Entity & Relation Recognition - Roth, Yih - 2002
40	Identifying semantic roles using combinatory categorial grammar - Gildea, Hockenmaier - 2003
37	Semantic role labeling by tagging syntactic chunks - Hacioglu, Pradhan, et al. - 2004
35	Use of deep linguistic features for the recognition and labeling of semantic arguments - Chen, Rambow - 2003
34	Neural networks for pattern recognition (Chapter 6.4: Modelling conditional distributions - Bishop - 1995
34	Text chunking based on a generalization of winnow - Zhang, Damerau, et al.
33	Semantic role parsing adding semantic structure to unstructured text - Pradhan, Hacioglu, et al. - 2003
32	A sequential model for multi class classification - Even-Zohar, Roth - 2001
32	Exploring evidence for shallow parsing - Li, Roth - 2001
21	Linear concepts and hidden variables - Grove, Roth - 2001
20	Phrase Recognition by Filtering and Ranking with Perceptrons - Carreras, Màrquez