國立虎尾科技大學 |

From Extractive to Abstractive Summarization: A Journey

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	From Extractive to Abstractive Summarization: A Journey/ by Parth Mehta, Prasenjit Majumder.
作者:	Mehta, Parth.
其他作者:	Majumder, Prasenjit.
面頁冊數:	XI, 116 p. 470 illus., 9 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Computer software—Reusability. -
電子資源:	https://doi.org/10.1007/978-981-13-8934-4
ISBN:	9789811389344

From Extractive to Abstractive Summarization: A Journey
Mehta, Parth.

From Extractive to Abstractive Summarization: A Journey[electronic resource] /by Parth Mehta, Prasenjit Majumder. - 1st ed. 2019. - XI, 116 p. 470 illus., 9 illus. in color.online resource.

Introduction.-Related Work -- Corpora and Evaluation for Text Summarization -- Domain Speciﬁc Summarization -- Improving sentence extraction through rank aggregation -- Leveraging content similarity in summaries for generating better ensembles.-Neural model for sentence compression -- Conclusion.

This book describes recent advances in text summarization, identifies remaining gaps and challenges, and proposes ways to overcome them. It begins with one of the most frequently discussed topics in text summarization – ‘sentence extraction’ –, examines the effectiveness of current techniques in domain-specific text summarization, and proposes several improvements. In turn, the book describes the application of summarization in the legal and scientific domains, describing two new corpora that consist of more than 100 thousand court judgments and more than 20 thousand scientific articles, with the corresponding manually written summaries. The availability of these large-scale corpora opens up the possibility of using the now popular data-driven approaches based on deep learning. The book then highlights the effectiveness of neural sentence extraction approaches, which perform just as well as rule-based approaches, but without the need for any manual annotation. As a next step, multiple techniques for creating ensembles of sentence extractors – which deliver better and more robust summaries – are proposed. In closing, the book presents a neural network-based model for sentence compression. Overall the book takes readers on a journey that begins with simple sentence extraction and ends in abstractive summarization, while also covering key topics like ensemble techniques and domain-specific summarization, which have not been explored in detail prior to this.

ISBN: 9789811389344

Standard No.: 10.1007/978-981-13-8934-4doiSubjects--Topical Terms:

1254984
Computer software—Reusability.

LC Class. No.: QA76.76.R44

Dewey Class. No.: 004.24

From Extractive to Abstractive Summarization: A Journey
LDR:03196nam a22004215i 4500 001 1010539
003 DE-He213
005 20200701221121.0
007 cr nn 008mamaa
008 210106s2019 si | s |||| 0|eng d
020 $a 9789811389344 $9 978-981-13-8934-4
024 7 $a 10.1007/978-981-13-8934-4 $2 doi
035 $a 978-981-13-8934-4
050 4 $a QA76.76.R44
050 4 $a TK5105.5956
072 7 $a UYD $2 bicssc
072 7 $a COM067000 $2 bisacsh
072 7 $a UYD $2 thema
072 7 $a UKR $2 thema
082 0 4 $a 004.24 $2 23
100 1 $a Mehta, Parth. $e editor. $1 https://orcid.org/0000-0002-4509-1298 $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1288664
245 1 0 $a From Extractive to Abstractive Summarization: A Journey $h [electronic resource] / $c by Parth Mehta, Prasenjit Majumder.
250 $a 1st ed. 2019.
264 1 $a Singapore : $b Springer Singapore : $b Imprint: Springer, $c 2019.
300 $a XI, 116 p. 470 illus., 9 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
505 0 $a Introduction.-Related Work -- Corpora and Evaluation for Text Summarization -- Domain Speciﬁc Summarization -- Improving sentence extraction through rank aggregation -- Leveraging content similarity in summaries for generating better ensembles.-Neural model for sentence compression -- Conclusion.
520 $a This book describes recent advances in text summarization, identifies remaining gaps and challenges, and proposes ways to overcome them. It begins with one of the most frequently discussed topics in text summarization – ‘sentence extraction’ –, examines the effectiveness of current techniques in domain-specific text summarization, and proposes several improvements. In turn, the book describes the application of summarization in the legal and scientific domains, describing two new corpora that consist of more than 100 thousand court judgments and more than 20 thousand scientific articles, with the corresponding manually written summaries. The availability of these large-scale corpora opens up the possibility of using the now popular data-driven approaches based on deep learning. The book then highlights the effectiveness of neural sentence extraction approaches, which perform just as well as rule-based approaches, but without the need for any manual annotation. As a next step, multiple techniques for creating ensembles of sentence extractors – which deliver better and more robust summaries – are proposed. In closing, the book presents a neural network-based model for sentence compression. Overall the book takes readers on a journey that begins with simple sentence extraction and ends in abstractive summarization, while also covering key topics like ensemble techniques and domain-specific summarization, which have not been explored in detail prior to this.
650 0 $a Computer software—Reusability. $3 1254984
650 0 $a Computer communication systems. $3 1115394
650 0 $a Application software. $3 528147
650 1 4 $a Performance and Reliability. $3 669802
650 2 4 $a Computer Communication Networks. $3 669310
650 2 4 $a Information Systems Applications (incl. Internet). $3 881699
700 1 $a Majumder, Prasenjit. $e editor. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1288662
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9789811389337
776 0 8 $i Printed edition: $z 9789811389351
776 0 8 $i Printed edition: $z 9789811389368
856 4 0 $u https://doi.org/10.1007/978-981-13-8934-4
912 $a ZDB-2-SCS
912 $a ZDB-2-SXCS
950 $a Computer Science (SpringerNature-11645)
950 $a Computer Science (R0) (SpringerNature-43710)