| Document Type
|
:
|
BL
|
| Record Number
|
:
|
890462
|
| Main Entry
|
:
|
Mehta, Parth
|
| Title & Author
|
:
|
From extractive to abstractive summarization : : a journey /\ Parth Mehta, Prasenjit Majumder.
|
| Publication Statement
|
:
|
Singapore :: Springer,, [2019]
|
| Page. NO
|
:
|
1 online resource (120 pages)
|
| ISBN
|
:
|
9789811389337
|
|
|
:
|
: 9789811389344
|
|
|
:
|
: 9789811389351
|
|
|
:
|
: 9789811389368
|
|
|
:
|
: 9811389330
|
|
|
:
|
: 9811389349
|
|
|
:
|
: 9811389357
|
|
|
:
|
: 9811389365
|
| Bibliographies/Indexes
|
:
|
Includes bibliographical references.
|
| Contents
|
:
|
Intro; Preface; Contents; About the Authors; 1 Introduction; 1.1 Book Organisation; 1.2 Types of Summarisation Techniques; 1.3 Extractive Summarisation; 1.4 Information Fusion and Ensemble Techniques; 1.5 Abstractive Summarisation; 1.6 Main Contributions; References; 2 Related Work; 2.1 Extractive Summarisation; 2.2 Ensemble Techniques for Extractive Summarisation; 2.3 Sentence Compression; 2.4 Domain-Specific Summarisation; 2.4.1 Legal Document Summarisation; 2.4.2 Scientific Article Summarisation; References; 3 Corpora and Evaluation for Text Summarisation; 3.1 DUC and TAC Datasets
|
|
|
:
|
3.2 Legal and Scientific Article Dataset3.3 Evaluation; 3.3.1 Precision and Recall; 3.3.2 BLEU; 3.3.3 ROUGE Measure; 3.3.4 Pyramid Score; 3.3.5 Human Evaluation; References; 4 Domain-Specific Summarisation; 4.1 Legal Document Summarisation; 4.1.1 Boosting Legal Vocabulary Using a Lexicon; 4.1.2 Weighted TextRank and LexRank; 4.1.3 Automatic Keyphrase Identification; 4.1.4 Attention-Based Sentence Extractor; 4.2 Scientific Article Summarisation; 4.3 Experiment Details; 4.3.1 Results; 4.4 Conclusion; References; 5 Improving Sentence Extraction Through Rank Aggregation; 5.1 Introduction
|
|
|
:
|
5.2 Motivation for Rank Aggregation5.3 Analysis of Existing Extractive Systems; 5.3.1 Experimental Setup; 5.4 Ensemble of Extractive Summarisation Systems; 5.4.1 Effect of Informed Fusion; 5.5 Discussion; 5.5.1 Determining the Robustness of Candidate Systems; 5.5.2 Qualitative Analysis of Summaries; References; 6 Leveraging Content Similarity in Summaries for Generating Better Ensembles; 6.1 Limitations of Consensus-Based Aggregation; 6.2 Proposed Approach for Content-Based Aggregation; 6.3 Document Level Aggregation; 6.3.1 Experimental Results; 6.4 Sentence Level Aggregation; 6.4.1 SentRank
|
|
|
:
|
6.4.2 GlobalRank6.4.3 LocalRank; 6.4.4 HybridRank; 6.4.5 Experimental Results; 6.5 Conclusion; References; 7 Neural Model for Sentence Compression; 7.1 Sentence Compression by Deletion; 7.2 Sentence Compression Using Sequence to Sequence Model; 7.2.1 Sentence Encoder; 7.2.2 Context Encoder; 7.2.3 Decoder; 7.2.4 Attention Module; 7.3 Exploiting SMT Techniques for Sentence Compression; 7.4 Results for Sentence Compression; 7.5 Limitations of Sentence Compression Techniques; 7.6 Overall System; References; 8 Conclusion; References; A Sample Document-Summary Pairs from DUC, Legal and ACL Corpus
|
|
|
:
|
B The Dictionary Built Using Legal Boost MethodC Summaries Generated Using Rank Aggregation; D Summaries Generated Using Content-Based Aggregation; E Visualising Compression on Sentences from Legal Documents
|
| Abstract
|
:
|
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.
|
| Subject
|
:
|
Automatic abstracting.
|
| Subject
|
:
|
Computational linguistics.
|
| Subject
|
:
|
Automatic abstracting.
|
| Subject
|
:
|
Computational linguistics.
|
| Dewey Classification
|
:
|
410.285
|
| LC Classification
|
:
|
P98
|
| Added Entry
|
:
|
Majumder, Prasenjit
|