Theme Assignment for Sentences Based on Head-Driven Patterns

Bo-Yeong KANG; Sung-Hyon MYAENG

doi:10.1093/ietisy/e89-d.1.377

Theme Assignment for Sentences Based on Head-Driven Patterns

Bo-Yeong KANG, Sung-Hyon MYAENG

Full Text Views

0

Share
Cite this

Summary :

Since sentences are the basic propositional units of text, knowing their themes should help in completing various tasks such as automatic summarization requiring the knowledge about the semantic content of text. Despite the importance of determining the theme of a sentence, however, few studies have investigated the problem of automatically assigning a theme to a sentence. In this paper, we examine the notion of sentence theme and propose an automatic scheme where head-driven patterns are used for theme assignment. We tested our scheme with sentences in encyclopedia articles and obtained a promising result of 98.96% in F-score for training data and 88.57% for testing data, which outperform the baseline using all but the head-driven patterns.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.1 pp.377-380

Publication Date: 2006/01/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.1.377

Type of Manuscript: LETTER

Category: Natural Language Processing

Cite this

Copy

Bo-Yeong KANG, Sung-Hyon MYAENG, "Theme Assignment for Sentences Based on Head-Driven Patterns" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 1, pp. 377-380, January 2006, doi: 10.1093/ietisy/e89-d.1.377.
Abstract: Since sentences are the basic propositional units of text, knowing their themes should help in completing various tasks such as automatic summarization requiring the knowledge about the semantic content of text. Despite the importance of determining the theme of a sentence, however, few studies have investigated the problem of automatically assigning a theme to a sentence. In this paper, we examine the notion of sentence theme and propose an automatic scheme where head-driven patterns are used for theme assignment. We tested our scheme with sentences in encyclopedia articles and obtained a promising result of 98.96% in F-score for training data and 88.57% for testing data, which outperform the baseline using all but the head-driven patterns.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.1.377/_p

Copy

@ARTICLE{e89-d_1_377,
author={Bo-Yeong KANG, Sung-Hyon MYAENG, },
journal={IEICE TRANSACTIONS on Information},
title={Theme Assignment for Sentences Based on Head-Driven Patterns},
year={2006},
volume={E89-D},
number={1},
pages={377-380},
abstract={Since sentences are the basic propositional units of text, knowing their themes should help in completing various tasks such as automatic summarization requiring the knowledge about the semantic content of text. Despite the importance of determining the theme of a sentence, however, few studies have investigated the problem of automatically assigning a theme to a sentence. In this paper, we examine the notion of sentence theme and propose an automatic scheme where head-driven patterns are used for theme assignment. We tested our scheme with sentences in encyclopedia articles and obtained a promising result of 98.96% in F-score for training data and 88.57% for testing data, which outperform the baseline using all but the head-driven patterns.},
keywords={},
doi={10.1093/ietisy/e89-d.1.377},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - Theme Assignment for Sentences Based on Head-Driven Patterns
T2 - IEICE TRANSACTIONS on Information
SP - 377
EP - 380
AU - Bo-Yeong KANG
AU - Sung-Hyon MYAENG
PY - 2006
DO - 10.1093/ietisy/e89-d.1.377
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2006
AB - Since sentences are the basic propositional units of text, knowing their themes should help in completing various tasks such as automatic summarization requiring the knowledge about the semantic content of text. Despite the importance of determining the theme of a sentence, however, few studies have investigated the problem of automatically assigning a theme to a sentence. In this paper, we examine the notion of sentence theme and propose an automatic scheme where head-driven patterns are used for theme assignment. We tested our scheme with sentences in encyclopedia articles and obtained a promising result of 98.96% in F-score for training data and 88.57% for testing data, which outperform the baseline using all but the head-driven patterns.
ER -