Aggregation via Set Partitioning for Natural Language Generation

Regina Barzilay; Mirella Lapata

Aggregation via Set Partitioning for Natural Language Generation

School of Informatics

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

Abstract

The role of aggregation in natural language generation is to combine two or more linguistic structures into a single sentence. The task is crucial for generating concise and readable texts. We present an efficient algorithm for automatically learning aggregation rules from a text and its related database. The algorithm treats aggregation as a set partitioning problem and uses a global inference procedure to find an optimal solution. Our experiments show that this approach yields substantial improvements over a clustering-based model which relies exclusively on local information.

Original language	English
Title of host publication	Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Place of Publication	Stroudsburg, PA, USA
Publisher	Association for Computational Linguistics
Pages	359-366
Number of pages	8
Publication status	Published - 2006

Access to Document

2006_Barzilay_Lapata_Aggregation via Set Partitioning for Natural Language GenerationFinal published version, 169 KB

http://www.aclweb.org/anthology/N/N06/N06-1046

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

Cite this

@inproceedings{4b16c1315e064818bc1a0805f57f0e02,

title = "Aggregation via Set Partitioning for Natural Language Generation",

abstract = "The role of aggregation in natural language generation is to combine two or more linguistic structures into a single sentence. The task is crucial for generating concise and readable texts. We present an efficient algorithm for automatically learning aggregation rules from a text and its related database. The algorithm treats aggregation as a set partitioning problem and uses a global inference procedure to find an optimal solution. Our experiments show that this approach yields substantial improvements over a clustering-based model which relies exclusively on local information.",

author = "Regina Barzilay and Mirella Lapata",

year = "2006",

language = "English",

pages = "359--366",

booktitle = "Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics",

publisher = "Association for Computational Linguistics",

}

Barzilay, R & Lapata, M 2006, Aggregation via Set Partitioning for Natural Language Generation. in Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics. Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 359-366. <http://www.aclweb.org/anthology/N/N06/N06-1046>

Aggregation via Set Partitioning for Natural Language Generation. / Barzilay, Regina; Lapata, Mirella.
Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2006. p. 359-366.

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

TY - GEN

T1 - Aggregation via Set Partitioning for Natural Language Generation

AU - Barzilay, Regina

AU - Lapata, Mirella

PY - 2006

Y1 - 2006

N2 - The role of aggregation in natural language generation is to combine two or more linguistic structures into a single sentence. The task is crucial for generating concise and readable texts. We present an efficient algorithm for automatically learning aggregation rules from a text and its related database. The algorithm treats aggregation as a set partitioning problem and uses a global inference procedure to find an optimal solution. Our experiments show that this approach yields substantial improvements over a clustering-based model which relies exclusively on local information.

AB - The role of aggregation in natural language generation is to combine two or more linguistic structures into a single sentence. The task is crucial for generating concise and readable texts. We present an efficient algorithm for automatically learning aggregation rules from a text and its related database. The algorithm treats aggregation as a set partitioning problem and uses a global inference procedure to find an optimal solution. Our experiments show that this approach yields substantial improvements over a clustering-based model which relies exclusively on local information.

M3 - Conference contribution

SP - 359

EP - 366

BT - Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics

PB - Association for Computational Linguistics

CY - Stroudsburg, PA, USA

ER -

Aggregation via Set Partitioning for Natural Language Generation

Abstract

Access to Document

Fingerprint

Projects

Statistical model for text-to-text generation

Cite this