Muutke küpsiste eelistusi

E-raamat: Computational Analysis of Storylines: Making Sense of Events

Edited by (Vrije Universiteit, Amsterdam), Edited by , Edited by (University of Colorado Boulder), Edited by (Carnegie Mellon University, Pennsylvania)
  • Formaat - PDF+DRM
  • Hind: 70,38 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

""Event structures have been at the heart of Linguistics and Artificial Intelligence. People can easily refer to changes in the world, identify their participants, distinguish relevant information, and have expectations of what can happen next. Part of this process is based on mechanisms which are similar to narratives. Narratives provide means for understanding and organizing information by creating connections that form storylines. Such narrative structures are at the heart of information sharing. But it remains extraordinarily difficult to detect events automatically, let alone to automatically construct stories from such event representations. Handling today's massive news streams demands multidimensional, multimodal, distributed approaches to capture events and narrative structures involved in a "story". The book explores these topics, both by providing materials for a better understanding of the state-of-the-art as well as by highlighting the pending challenges in the area of events and storylines.Current research in this area is lively but fragmented and, for some topics (e.g. storyline representation and evaluation) still at early stages.""--

Arvustused

'Events are a key aspect of language meaning and the storylines underlying discourse. This book presents an accessible and comprehensive examination of events in language - from the philosophical and linguistic foundations to state of the art computational techniques for identifying, representing and reasoning about events and storylines.' James Allen, University of Rochester and Institute of Human and Machine Cognition 'There is no technology with more potential to revolutionise digital media than the computational processing of stories. This comprehensive guide covers the field of event and storyline analysis from first principles to the state of the art. Anyone doing technical work in news innovation or future media should read this.' David Caswell, Executive Product Manager, BBC News Labs 'Finally, a compendium of key, state-of-the-art ideas in narrative understanding, allowing researchers to see the big picture. Caselli, Hovy, Palmer, and Vossen have not only assembled key papers, but also created a beautiful conceptual overview of the field a must-read for any researcher interested in narratives and storylines.' Peter Clark, Allen Institute for AI

Muu info

A review of recent computational (deep learning) approaches to understanding news and nonfiction stories.
List of Contributors xi
Introduction and Overview 1(20)
Part One Foundational Components Of Storylines 21(122)
1 The Role of Event-Based Representations and Reasoning in Language
23(24)
James Pustejovsky
1.1 Introduction
23(2)
1.2 Introducing Situations and Events
25(8)
1.3 Modeling the Substructure of Events
33(5)
1.4 Enriching VerbNet with Event Dynamics
38(4)
1.5 Conclusions
42(5)
2 The Rich Event Ontology: Ontological Hub for Event Representations
47(20)
Claire Bonial
Susan W. Brown
Martha Palmer
Ghazaleh Kazeminejad
2.1 Introduction
47(1)
2.2 Ontologies
48(8)
2.3 Semantic Role Labeling
56(5)
2.4 Conclusions, Gaps, and Future Work
61(6)
3 Decomposing Events and Storylines
67(20)
William Croft
Pavlina Kalm
Michael Regan
3.1 Introduction: Events within Stories and Events within Events
67(2)
3.2 Constructions as Well as Verbs Determine the Internal Structure of Events
69(2)
3.3 Time and Qualitative State (Change)
71(3)
3.4 Causation
74(4)
3.5 Annotation Scheme
78(2)
3.6 Visualization
80(2)
3.7 Conclusion
82(5)
4 Extracting and Aligning Timelines
87(19)
Mark A. Finlayson
Andres Cremisini
Mustafa Ocal
4.1 Introduction
87(2)
4.2 Extracting Timelines
89(6)
4.3 Aligning Timelines
95(5)
4.4 Bringing It All Together
100(1)
4.5 Conclusion
101(5)
5 Event Causality
106(19)
Paramita Mirza
5.1 Introduction
106(2)
5.2 Modelling Causal Relations
108(2)
5.3 Causal Annotation in Natural Language Text
110(4)
5.4 Extracting Event Causality
114(3)
5.5 Causal Commonsense Discovery
117(3)
5.6 Conclusions
120(5)
6 A Narratology-Based Framework for Storyline Extraction
125(18)
Piek Vossen
Tommaso Caselli
Roxane Segers
6.1 Introduction
125(1)
6.2 A Narratology-Grounded Framework for Storylines Identification
126(4)
6.3 From Theory to Data: Annotating Causelines and Storylines
130(4)
6.4 Validating Causelines and Extracting Storylines
134(3)
6.5 Conclusion
137(6)
Part Two Connecting The Dots: Resources, Tools, And Representations 143(117)
7 The Richer Event Description Corpus for Event-Event Relations
145(18)
Tim O'Gorman
Kristin Wright-Bettner
Martha Palmer
7.1 Introduction
145(1)
7.2 A Comparison of Event Annotation Choices
146(9)
7.3 Long-Distance Relations in RED: Contains, Causality, and Coreference
155(1)
7.4 Studying RED Impact on Event Ordering
156(2)
7.5 Conclusions
158(5)
8 Low-Resource Event Extraction via Share-and-Transfer and Remaining Challenges
163(24)
Heng Ji
Clare Voss
8.1 Introduction
163(3)
8.2 Approach Overview
166(1)
8.3 Share: Construction of Common Semantic Space
167(8)
8.4 Transfer: From High- to Low-Resource Setting
175(2)
8.5 Transfer Learning Performance
177(1)
8.6 Remaining Challenges
177(5)
8.7 Conclusions and Future Research Directions
182(5)
9 Reading Certainty across Sources
187(16)
Benjamin Miller
9.1 Introduction
187(5)
9.2 Background
192(2)
9.3 Methods
194(1)
9.4 Results
195(3)
9.5 Discussion
198(2)
9.6 Conclusion
200(3)
10 Narrative Homogeneity and Heterogeneity in Document Categories
203(18)
Dan Simonson
Anthony R. Davis
10.1 Introduction: Narrative Schemas and Their Evaluations
203(2)
10.2 Background
205(1)
10.3 Data and Schema Generation
206(2)
10.4 Evidence through NASTEA Task
208(5)
10.5 Evidence through Schema Stability
213(3)
10.6 Discussion
216(1)
10.7 Conclusions
217(4)
11 Exploring Machine Learning Techniques for Linking Event Templates
221(19)
Jakub Piskorski
Fredi Saric
Vanni Zavarella
Martin Atkinson
11.1 Introduction
221(3)
11.2 Task Description
224(1)
11.3 Event Similarity Metrics
225(5)
11.4 Experiments
230(6)
11.5 Conclusions
236(4)
12 Semantic Storytelling: From Experiments and Prototypes to a Technical Solution
240(20)
Georg Rehm
Karolina Zaczynska
Peter Bourgonje
Malte Ostendorff
Julian Moreno-Schneider
Maria Berger
Jens Rauenbusch
Andre Schmidt
Mikka Wild
Joachim Banger
Joachim Quantz
Jan Thomsen
Rolf Fricke
12.1 Introduction: Technologies for Content Curation
240(2)
12.2 Semantic Storytelling: Selected Components
242(4)
12.3 Semantic Storytelling in Industry Use Cases
246(4)
12.4 Towards a Flexible and Robust Technology Solution for Semantic Storytelling
250(2)
12.5 Related Work
252(2)
12.6 Conclusions and Future Work
254(6)
Author Index 260
Tommaso Caselli is an Assistant Professor in Computational Semantics at the University of Groningen. He received his PhD in computational linguistics on temporal processing of texts from the University of Pisa. His main research areas are in discourse processing, event extraction, and (event) sentiment analysis. He is one of the founders of the 'Event and Stories in the News' workshop series, and is currently working on developing computational models and NLP tools to extract plot structures from news. He took part in organizing semantic evaluation campaigns in NLP for English and Italian. Eduard Hovy is a Research Professor at the Language Technology Institute at Carnegie Mellon University. He was was awarded honorary doctorates from the National Distance Education University (UNED) in Madrid in 2013 and the University of Antwerp in 2015. He is one of the initial 17 Fellows of the Association for Computational Linguistics (ACL). His research contributions include the co-development of the ROUGE text summarization evaluation method, the BLANC coreference evaluation method, the Omega ontology, the Webclopedia QA Typology, the FEMTI machine translation evaluation classification, the DAP text harvesting method, the OntoNotes corpus, and a model of Structured Distributional Semantics. Martha Palmer is a Professor at the University of Colorado in Linguistics, Computer Science and Cognitive Science. She is a AAAI Fellow and an ACL Fellow. She works on trying to capture elements of the meanings of words that can comprise automatic representations of complex sentences and documents. She is a co-editor of Linguistic Issues in Language Technology, and has been on the CLJ Editorial Board and a co-editor of JNLE. She is a past President of the Association for Computational Linguistics, past Chair of SIGLEX and SIGHAN, and was the Director of the 2011 Linguistics Institute held in Boulder, CO. Piek Vossen is Professor at Vrije Universiteit Amsterdam. He is the co-founder and co-president of the Global Wordnet Association, organizing the international Wordnet conferences since 2002. In 2013, he received the Dutch Spinoza prize for his research. He used this prize to launch a series of projects among which the structuring of news streams using storylines and reader/writer perspectives. Vossen's current main research focuses on cross-document event co-reference and perspective modeling of multiple sources with respect to event data and modeling event implications, as well as event timelines and storylines.