Natural Language Processing for the Semantic Web (Synthesis Lectures on the Semantic Web: Theory and Technology, 15)

This book introduces core natural language processing (NLP) technologies to non-experts in an easily accessible way, as a series of building blocks that lead the user to understand key technologies, why they are required, and how to integrate them into Semantic Web applications. Natural language processing and Semantic Web technologies have different, but complementary roles in data management. Combining these two technologies enables structured and unstructured data to merge seamlessly. Semantic Web technologies aim to convert unstructured data to meaningful representations, which benefit enormously from the use of NLP technologies, thereby enabling applications such as connecting text to Linked Open Data, connecting texts to each other, semantic searching, information visualization, and modeling of user behavior in online networks.

The first half of this book describes the basic NLP processing tools: tokenization, part-of-speech tagging, and morphological analysis, in addition to the main tools required for an information extraction system (named entity recognition and relation extraction) which build on these components. The second half of the book explains how Semantic Web and NLP technologies can enhance each other, for example via semantic annotation, ontology linking, and population. These chapters also discuss sentiment analysis, a key component in making sense of textual data, and the difficulties of performing NLP on social media, as well as some proposed solutions. The book finishes by investigating some applications of these tools, focusing on semantic search and visualization, modeling user behavior, and an outlook on the future.

Diana Maynard is a Senior Researcher at the University of Sheffield. She obtained a Ph.D. on the topic of Automatic Term Recognition from Manchester Metropolitan University in 2000, and has been involved in research in NLP and text mining since 1994. Her main research interests are in information extraction, opinion mining, social media analysis, term extraction, ontology development, and the Semantic Web. Since 2000 she has led the development of USFD's open-source multilingual IE tools, and has led research on a number of UK and EU projects including COMRADES, DecarboNet, Arcomem, KnowledgeWeb, and NeOn. She regularly provides consultancy and training on NLP and GATE use in the public and private sector, and is advisor to two start-up companies. She has published extensively, organized national and international conferences and workshops, given numerous invited talks and tutorials, reviews regularly for conferences and journals, and was the organizer of the ISWC Semantic Web Challenge from 2010-2013. She has examined a number of Ph.D.s in the UK and abroad, is the Book Review Editor for the Journal of Natural Language Engineering, and reviews project proposals for the ESRC and RNTL.

Kalina Bontcheva is the holder of a prestigious EPSRC career acceleration fellowship, working on text mining and summarization of social media. Dr. Bontcheva received her Ph.D. on the topic of adaptive hypertext generation from the University of Sheffield in 2001. She has been a leading developer of the GATE text analytics infrastructure since 1999. Her main interests are software infrastructures for NLP, information extraction, natural language generation, and text summarization. Kalina Bontcheva is currently coordinating the PHEME FP7 project on computing veracity of social media content, as well as leading the Sheffield teams in TrendMiner, DecarboNet, and uComp. Previously she coordinated the EC-funded TAO STREP project on transitioning applications to ontologies and contributed to the MUSING, SEKT, and MIAKT projects. Prof. Bontcheva is co-organizer of the bi-annual conference "Recent Advances in Natural Language Processing," co-chair of the Information Extraction track of ACL'2010 and EMNLP'2010, a demo co-chair for ACL'2014, an area co-chair for UMAP'2014, and a PC cochair for UMAP'2015. She has published extensively in high-profile journals and conferences and delivered invited talks and tutorials.

Isabelle Augenstein is a Research Associate in the UCL Machine Reading group. Prior to that, she was a Research Associate in the Sheffield NLP group and completed a Ph.D. thesis at the University of Sheffield on the topic of relation extraction from the Web. Before joining the University of Sheffield in October 2012 she studied Computational Linguistics at the Department of Computational Linguistics, Heidelberg University, and was a part-time research assistant at AIFB, Karlsruhe Institute of Technology. Isabelle Augenstein's main research interests are information extraction, knowledge base population, and machine learning for natural language processing. Her research focuses on methods which do not require manually annotated training data and instead exploit background information, such as Linked Data. Her current work focuses on automatic knowledge base construction for scientific publications. She has published in high-profile conferences and journals such as ACL, EMNLP, ISWC, and the Semantic Web journal and regularly reviews for conferences. She has given tutorials and organized hands-on sessions on natural language processing for the Semantic Web at the ESWC Summer Schools in 2014 and 2015.