Unsupervised Induction of Frame-Semantic Representations

Ashutosh Modi; Ivan Titov; Alexandre Klementiev

Unsupervised Induction of Frame-Semantic Representations

Ashutosh Modi, Ivan Titov, Alexandre Klementiev

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

Abstract

The frame-semantic parsing task is challenging for supervised techniques, even for those few languages where relatively large amounts of labeled data are available. In this preliminary work, we consider unsupervised induction of frame-semantic representations. An existing state-of-the-art Bayesian model for PropBank-style unsupervised semantic role induction (Titov and Klementiev, EACL 2012) is extended to jointly induce semantic frames and their roles. We evaluate the model performance both quantitatively and qualitatively by comparing the induced representation against FrameNet annotations.

Original language	English
Title of host publication	Proceedings of the NAACL-HLT 2012 Workshop on Inducing Linguistic Structure
Place of Publication	Montreal, Canada
Number of pages	7
Publication status	Published - 1 Jun 2012

Access to Document

http://www.aclweb.org/anthology/W12-1901Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{5c3e5b6424064def9cb540d6434b4f8c,

title = "Unsupervised Induction of Frame-Semantic Representations",

abstract = "The frame-semantic parsing task is challenging for supervised techniques, even for those few languages where relatively large amounts of labeled data are available. In this preliminary work, we consider unsupervised induction of frame-semantic representations. An existing state-of-the-art Bayesian model for PropBank-style unsupervised semantic role induction (Titov and Klementiev, EACL 2012) is extended to jointly induce semantic frames and their roles. We evaluate the model performance both quantitatively and qualitatively by comparing the induced representation against FrameNet annotations.",

author = "Ashutosh Modi and Ivan Titov and Alexandre Klementiev",

year = "2012",

month = jun,

day = "1",

language = "English",

booktitle = "Proceedings of the NAACL-HLT 2012 Workshop on Inducing Linguistic Structure",

}

TY - GEN

T1 - Unsupervised Induction of Frame-Semantic Representations

AU - Modi, Ashutosh

AU - Titov, Ivan

AU - Klementiev, Alexandre

PY - 2012/6/1

Y1 - 2012/6/1

N2 - The frame-semantic parsing task is challenging for supervised techniques, even for those few languages where relatively large amounts of labeled data are available. In this preliminary work, we consider unsupervised induction of frame-semantic representations. An existing state-of-the-art Bayesian model for PropBank-style unsupervised semantic role induction (Titov and Klementiev, EACL 2012) is extended to jointly induce semantic frames and their roles. We evaluate the model performance both quantitatively and qualitatively by comparing the induced representation against FrameNet annotations.

AB - The frame-semantic parsing task is challenging for supervised techniques, even for those few languages where relatively large amounts of labeled data are available. In this preliminary work, we consider unsupervised induction of frame-semantic representations. An existing state-of-the-art Bayesian model for PropBank-style unsupervised semantic role induction (Titov and Klementiev, EACL 2012) is extended to jointly induce semantic frames and their roles. We evaluate the model performance both quantitatively and qualitatively by comparing the induced representation against FrameNet annotations.

M3 - Conference contribution

BT - Proceedings of the NAACL-HLT 2012 Workshop on Inducing Linguistic Structure

CY - Montreal, Canada

ER -

Unsupervised Induction of Frame-Semantic Representations

Abstract

Access to Document

Fingerprint

Cite this