Computational Analysis of Storylines: Making Sense of Events

Description

Event structures are central in Linguistics and Artificial Intelligence research: 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 similar to narratives, which are at the heart of information sharing. But it remains difficult to automatically detect events or automatically construct stories from such event representations. This book explores how to handle today's massive news streams and provides multidimensional, multimodal, and distributed approaches, like automated deep learning, to capture events and narrative structures involved in a 'story'. This overview of the current state-of-the-art on event extraction, temporal and casual relations, and storyline extraction aims to establish a new multidisciplinary research community with a common terminology and research agenda. Graduate students and researchers in natural language processing, computational linguistics, and media studies will benefit from this book.

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.

'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