Cross-linguistic Projection of Role-Semantic Information

Sebastian Padó; Maria Lapata

Cross-linguistic Projection of Role-Semantic Information

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper considers the problem of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We introduce a general framework for semantic projection which exploits parallel texts, is relatively inexpensive and can potentially reduce the amount of effort involved in creating semantic resources. We propose projection models that exploit lexical and syntactic information. Experimental results on an English German parallel corpus demonstrate the advantages of this approach.

Original language	English
Title of host publication	Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP)
Publisher	Association for Computational Linguistics
Pages	859-866
Number of pages	8
Publication status	Published - 2005

Access to Document

http://www.aclweb.org/anthology/H05-1108

Statistical model for text-to-text generation
Lapata, M.
EPSRC
1/02/05 → 28/02/11
Project: Research

Cite this

@inproceedings{475f8d1a086343859d3d3291aee1d3bf,

title = "Cross-linguistic Projection of Role-Semantic Information",

abstract = "This paper considers the problem of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We introduce a general framework for semantic projection which exploits parallel texts, is relatively inexpensive and can potentially reduce the amount of effort involved in creating semantic resources. We propose projection models that exploit lexical and syntactic information. Experimental results on an English German parallel corpus demonstrate the advantages of this approach.",

author = "Sebastian Pad{\'o} and Maria Lapata",

year = "2005",

language = "English",

pages = "859--866",

booktitle = "Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP)",

publisher = "Association for Computational Linguistics",

}

Cross-linguistic Projection of Role-Semantic Information. / Padó, Sebastian; Lapata, Maria.
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP). Association for Computational Linguistics, 2005. p. 859-866.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Cross-linguistic Projection of Role-Semantic Information

AU - Padó, Sebastian

AU - Lapata, Maria

PY - 2005

Y1 - 2005

N2 - This paper considers the problem of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We introduce a general framework for semantic projection which exploits parallel texts, is relatively inexpensive and can potentially reduce the amount of effort involved in creating semantic resources. We propose projection models that exploit lexical and syntactic information. Experimental results on an English German parallel corpus demonstrate the advantages of this approach.

AB - This paper considers the problem of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We introduce a general framework for semantic projection which exploits parallel texts, is relatively inexpensive and can potentially reduce the amount of effort involved in creating semantic resources. We propose projection models that exploit lexical and syntactic information. Experimental results on an English German parallel corpus demonstrate the advantages of this approach.

M3 - Conference contribution

SP - 859

EP - 866

BT - Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP)

PB - Association for Computational Linguistics

ER -

Cross-linguistic Projection of Role-Semantic Information

Abstract

Access to Document

Fingerprint

Projects

Statistical model for text-to-text generation

Cite this