Acquisition of Domain-specific Patterns for Single Document Summarization and Information Extraction

Mian Du; Roman Yangarber

Acquisition of Domain-specific Patterns for Single Document Summarization and Information Extraction

Avdelningen för datavetenskap

Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review

Sammanfattning

Single-document summarization aims to reduce the size of a text document while preserving the most important information. Much work has been done on open-domain summarization. This paper presents an automatic way to mine domain-specific patterns from text documents. With a small amount of effort required for manual selection, these patterns can be used for domain-specific scenario-based document summarization and information extraction. Our evaluation shows that scenario-based document summarization can both filter irrelevant documents and create summaries for relevant documents within the specified domain.

Originalspråk	engelska
Titel på värdpublikation	Proceedings of the The Second International Conference on Artificial Intelligence and Pattern Recognition, Shenzhen, China, 2015
Redaktörer	Yimin Zhou
Antal sidor	10
Förlag	The Society of Digital Information and Wireless Communications (SDIWC)
Utgivningsdatum	17 apr. 2015
ISBN (elektroniskt)	978-1-941968-09-3
Status	Publicerad - 17 apr. 2015
MoE-publikationstyp	A4 Artikel i en konferenspublikation
Evenemang	International Conference on Artificial Intelligence and Pattern Recognition - ShenZhen, Kina Varaktighet: 16 apr. 2015 → 18 apr. 2015 Konferensnummer: 2 (AIPR2015)

Bibliografisk information

AIPR 2015.

Vetenskapsgrenar

113 Data- och informationsvetenskap

Åtkomst av dokument

2015-aipr-patternsAccepterat manuskript från författare, 651 KB

LLL: Language Learning Lab
Yangarber, R. (Projektledare), Katinskaia, A. (Deltagare), Hou, J. (Deltagare), Furlan, G. (Deltagare) & Kylliäinen, I. P. (Deltagare)
Projekt: Forskningsprojekt

Citera det här

@inproceedings{62c4e550d7774234ba8b46874ee2f5b2,

title = "Acquisition of Domain-specific Patterns for Single Document Summarization and Information Extraction",

abstract = "Single-document summarization aims to reduce the size of a text document while preserving the most important information. Much work has been done on open-domain summarization. This paper presents an automatic way to mine domain-specific patterns from text documents. With a small amount of effort required for manual selection, these patterns can be used for domain-specific scenario-based document summarization and information extraction. Our evaluation shows that scenario-based document summarization can both filter irrelevant documents and create summaries for relevant documents within the specified domain.",

keywords = "113 Computer and information sciences, Information Extraction, Machine learning, Data Mining",

author = "Mian Du and Roman Yangarber",

note = "AIPR 2015. ; International Conference on Artificial Intelligence and Pattern Recognition ; Conference date: 16-04-2015 Through 18-04-2015",

year = "2015",

month = apr,

day = "17",

language = "English",

editor = "Zhou, { Yimin}",

booktitle = "Proceedings of the The Second International Conference on Artificial Intelligence and Pattern Recognition, Shenzhen, China, 2015",

publisher = "The Society of Digital Information and Wireless Communications (SDIWC) ",

address = "International",

}

Du, M & Yangarber, R 2015, Acquisition of Domain-specific Patterns for Single Document Summarization and Information Extraction. i Y Zhou (red.), Proceedings of the The Second International Conference on Artificial Intelligence and Pattern Recognition, Shenzhen, China, 2015. The Society of Digital Information and Wireless Communications (SDIWC) , International Conference on Artificial Intelligence and Pattern Recognition, ShenZhen, Kina, 16/04/2015.

Acquisition of Domain-specific Patterns for Single Document Summarization and Information Extraction. / Du, Mian; Yangarber, Roman.
Proceedings of the The Second International Conference on Artificial Intelligence and Pattern Recognition, Shenzhen, China, 2015. red. / Yimin Zhou. The Society of Digital Information and Wireless Communications (SDIWC) , 2015.

Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review

TY - GEN

T1 - Acquisition of Domain-specific Patterns for Single Document Summarization and Information Extraction

AU - Du, Mian

AU - Yangarber, Roman

N1 - Conference code: 2 (AIPR2015)

PY - 2015/4/17

Y1 - 2015/4/17

N2 - Single-document summarization aims to reduce the size of a text document while preserving the most important information. Much work has been done on open-domain summarization. This paper presents an automatic way to mine domain-specific patterns from text documents. With a small amount of effort required for manual selection, these patterns can be used for domain-specific scenario-based document summarization and information extraction. Our evaluation shows that scenario-based document summarization can both filter irrelevant documents and create summaries for relevant documents within the specified domain.

AB - Single-document summarization aims to reduce the size of a text document while preserving the most important information. Much work has been done on open-domain summarization. This paper presents an automatic way to mine domain-specific patterns from text documents. With a small amount of effort required for manual selection, these patterns can be used for domain-specific scenario-based document summarization and information extraction. Our evaluation shows that scenario-based document summarization can both filter irrelevant documents and create summaries for relevant documents within the specified domain.

KW - 113 Computer and information sciences

KW - Information Extraction

KW - Machine learning

KW - Data Mining

M3 - Conference contribution

BT - Proceedings of the The Second International Conference on Artificial Intelligence and Pattern Recognition, Shenzhen, China, 2015

A2 - Zhou, Yimin

PB - The Society of Digital Information and Wireless Communications (SDIWC)

T2 - International Conference on Artificial Intelligence and Pattern Recognition

Y2 - 16 April 2015 through 18 April 2015

ER -

Acquisition of Domain-specific Patterns for Single Document Summarization and Information Extraction

Sammanfattning

Bibliografisk information

Vetenskapsgrenar

Åtkomst av dokument

Projekt

LLL: Language Learning Lab

Citera det här