Building and refining rhetorical-semantic relation models

Sasha Blair-Goldensohn; Kathleen R. McKeown; Owen C. Rambow

Building and refining rhetorical-semantic relation models

Sasha Blair-Goldensohn
, Kathleen R. McKeown
, Owen C. Rambow

Linguistics

Stony Brook University

Alphabet Inc.
Columbia University

Research output: Contribution to conference › Paper › peer-review

33 Scopus citations

Abstract

We report results of experiments which build and refine models of rhetorical-semantic relations such as Cause and Contrast. We adopt the approach of Marcu and Echihabi (2002), using a small set of patterns to build relation models, and extend their work by refining the training and classification process using parameter optimization, topic segmentation and syntactic parsing. Using human-annotated and automatically-extracted test sets, we find that each of these techniques results in improved relation classification accuracy.

Original language	English
Pages	428-435
Number of pages	8
State	Published - 2007
Event	Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007 - Rochester, NY, United States Duration: Apr 22 2007 → Apr 27 2007

Conference

Conference	Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007
Country/Territory	United States
City	Rochester, NY
Period	04/22/07 → 04/27/07

Cite this

@conference{5a586150a4fb4f0f9367ce6aca9681de,

title = "Building and refining rhetorical-semantic relation models",

abstract = "We report results of experiments which build and refine models of rhetorical-semantic relations such as Cause and Contrast. We adopt the approach of Marcu and Echihabi (2002), using a small set of patterns to build relation models, and extend their work by refining the training and classification process using parameter optimization, topic segmentation and syntactic parsing. Using human-annotated and automatically-extracted test sets, we find that each of these techniques results in improved relation classification accuracy.",

author = "Sasha Blair-Goldensohn and McKeown, \{Kathleen R.\} and Rambow, \{Owen C.\}",

year = "2007",

language = "English",

pages = "428--435",

note = "Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007 ; Conference date: 22-04-2007 Through 27-04-2007",

}

Building and refining rhetorical-semantic relation models. / Blair-Goldensohn, Sasha; McKeown, Kathleen R.; Rambow, Owen C.
2007. 428-435 Paper presented at Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007, Rochester, NY, United States.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Building and refining rhetorical-semantic relation models

AU - Blair-Goldensohn, Sasha

AU - McKeown, Kathleen R.

AU - Rambow, Owen C.

PY - 2007

Y1 - 2007

N2 - We report results of experiments which build and refine models of rhetorical-semantic relations such as Cause and Contrast. We adopt the approach of Marcu and Echihabi (2002), using a small set of patterns to build relation models, and extend their work by refining the training and classification process using parameter optimization, topic segmentation and syntactic parsing. Using human-annotated and automatically-extracted test sets, we find that each of these techniques results in improved relation classification accuracy.

AB - We report results of experiments which build and refine models of rhetorical-semantic relations such as Cause and Contrast. We adopt the approach of Marcu and Echihabi (2002), using a small set of patterns to build relation models, and extend their work by refining the training and classification process using parameter optimization, topic segmentation and syntactic parsing. Using human-annotated and automatically-extracted test sets, we find that each of these techniques results in improved relation classification accuracy.

UR - https://www.scopus.com/pages/publications/77956609861

M3 - Paper

SP - 428

EP - 435

T2 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007

Y2 - 22 April 2007 through 27 April 2007

ER -

Building and refining rhetorical-semantic relation models

Abstract

Conference

Other files and links

Fingerprint

Cite this