嶺東科技大學 |

Language: English

Back

Methods for mining and summarizing text conversations

Record Type:	Language materials, printed : monographic
Author:	CareniniGiuseppe,
Alternative Intellectual Responsibility:	MurrayGabriel,
Alternative Intellectual Responsibility:	NgRaymond Tak-yan,
Place of Publication:	[San Rafael, Calif.]
Published:	Morgan & Claypool;
Year of Publication:	c2011
Description:	x, 120 p.ill. : 24 cm.;
Series:	Synthesis lectures on data management
Subject:	Natural language processing (Computer science) -
Subject:	Data mining. -
Summary:	Due to the Internet Revolution, human conversational data--in written forms--are accumulating at a phenomenal rate. At the same time, improvements in speech technology enable many spoken conversations to be transcribed. Individuals and organizations engage in email exchanges, face-to-face meetings, blogging, texting and other social media activities. The advances in natural language processing provide ample opportunities for these "informal documents" to be analyzed and mined, thus creating numerous new and valuable applications. This book presents a set of computational methods to extract information from conversational data, and to provide natural language summaries of the data. The book begins with an overview of basic concepts, such as the differences between extractive and abstractive summaries, and metrics for evaluating the effectiveness of summarization and various extraction tasks. It also describes some of the benchmark corpora used in the literature. The book introduces extraction and mining methods for performing subjectivity and sentiment detection, topic segmentation and modeling, and the extraction of conversational structure. It also describes frameworks for conducting dialogue act recognition, decision and action item detection,and extraction of thread structure.There is a specific focus on performing all these tasks on conversational data, such as meeting transcripts (which exemplify synchronous conversations) and emails (which exemplify asynchronous conversations)Very recent approaches to deal with blogs, discussion forums and microblogs (e.g.,Twitter) are also discussed. The second half of this book focuses on natural language summarization of conversational data. It gives an overview of several extractive and abstractive summarizers developed for emails, meetings, blogs and forums. It also describes attempts for building multi-modal summarizers. Last but not least, the book concludes with thoughts on topics for further development
ISBN:	978-1-60845-390-0pbk.
ISBN:	1-60845-390-1pbk.

Methods for mining and summarizing text conversations
Carenini, Giuseppe

Methods for mining and summarizing text conversations / Giuseppe Carenini, Gabriel Murray, and Raymond Ng - [San Rafael, Calif.] : Morgan & Claypool, c2011. - x, 120 p. ; ill. ; 24 cm.. - (Synthesis lectures on data management ; #17).
Includes bibliographical references (p. 107-118).
ISBN 978-1-60845-390-0ISBN 1-60845-390-1
Natural language processing (Computer science)Data mining.

Murray, Gabriel

Methods for mining and summarizing text conversations
LDR:02742nam0 2200217 450 001 259955
005 20111215023753.0
010 1 $a 978-1-60845-390-0 $b pbk. $d NT$1041
010 1 $a 1-60845-390-1 $b pbk. $d NT$1041
100 $a 20120105d2011 m y0engy01 b
101 0 $a eng
102 $a us
105 $a a a 000zy
200 1 $a Methods for mining and summarizing text conversations $f Giuseppe Carenini, Gabriel Murray, and Raymond Ng
210 $a [San Rafael, Calif.] $d c2011 $c Morgan & Claypool
215 1 $a x, 120 p. $c ill. $d 24 cm.
225 2 # $a Synthesis lectures on data management $v #17
320 $a Includes bibliographical references (p. 107-118)
330 $a Due to the Internet Revolution, human conversational data--in written forms--are accumulating at a phenomenal rate. At the same time, improvements in speech technology enable many spoken conversations to be transcribed. Individuals and organizations engage in email exchanges, face-to-face meetings, blogging, texting and other social media activities. The advances in natural language processing provide ample opportunities for these "informal documents" to be analyzed and mined, thus creating numerous new and valuable applications. This book presents a set of computational methods to extract information from conversational data, and to provide natural language summaries of the data. The book begins with an overview of basic concepts, such as the differences between extractive and abstractive summaries, and metrics for evaluating the effectiveness of summarization and various extraction tasks. It also describes some of the benchmark corpora used in the literature. The book introduces extraction and mining methods for performing subjectivity and sentiment detection, topic segmentation and modeling, and the extraction of conversational structure. It also describes frameworks for conducting dialogue act recognition, decision and action item detection,and extraction of thread structure.There is a specific focus on performing all these tasks on conversational data, such as meeting transcripts (which exemplify synchronous conversations) and emails (which exemplify asynchronous conversations)Very recent approaches to deal with blogs, discussion forums and microblogs (e.g.,Twitter) are also discussed. The second half of this book focuses on natural language summarization of conversational data. It gives an overview of several extractive and abstractive summarizers developed for emails, meetings, blogs and forums. It also describes attempts for building multi-modal summarizers. Last but not least, the book concludes with thoughts on topics for further development
410 0 $1 2001 $a Synthesis lectures on data management $v #17
606 # $a Natural language processing (Computer science) $3 119357
606 # $a Data mining. $3 92770
676 $a 029.5
700 0 $a Carenini $b Giuseppe $3 271665
701 1 $a Murray $b Gabriel $3 271664
701 1 $a Ng $b Raymond Tak-yan $3 275710
801 0 $a cw $b 嶺東科技大學圖書館 $g CCR