Domain-Sensitive Temporal Tagging. Jannik Strötgen

      Series ISSN

      Print 1947-4040 Electronic 1947-4059

      Domain-Sensitive Temporal Tagging

      Jannik Strötgen

      Max Planck Institute for Informatics, Saarbrücken, Germany

      Michael Gertz

      Heidelberg University, Germany

       SYNTHESIS LECTURES ON HUMAN LANGUAGE TECHNOLOGIES #36

       ABSTRACT

      This book covers the topic of temporal tagging, the detection of temporal expressions and the normalization of their semantics to some standard format. It places a special focus on the challenges and opportunities of domain-sensitive temporal tagging. After providing background knowledge on the concept of time, the book continues with a comprehensive survey of current research on temporal tagging. The authors provide an overview of existing techniques and tools, and highlight key issues that need to be addressed. This book is a valuable resource for researchers and application developers who need to become familiar with the topic and want to know the recent trends, current tools and techniques, as well as different application domains in which temporal information is of utmost importance.

      Due to the prevalence of temporal expressions in diverse types of documents and the importance of temporal information in any information space, temporal tagging is an important task in natural language processing (NLP), and applications of several domains can benefit from the output of temporal taggers to provide more meaningful and useful results.

      In recent years, temporal tagging has been an active field in NLP and computational linguistics. Several approaches to temporal tagging have been proposed, annotation standards have been developed, gold standard data sets have been created, and research competitions have been organized. Furthermore, some temporal taggers have also been made publicly available so that temporal tagging output is not just exploited in research, but is finding its way into real world applications. In addition, this book particularly focuses on domain-specific temporal tagging of documents. This is a crucial aspect as different types of documents (e.g., news articles, narratives, and colloquial texts) result in diverse challenges for temporal taggers and should be processed in a domain-sensitive manner.

       KEYWORDS

      temporal tagging, temporal expressions, temporal annotation, time, time extraction, time recognition, time normalization, temporal information, domain sensitivity, cross-domain temporal tagging, domain-sensitive temporal tagging, information extraction, temporal information extraction, TIMEX3, TimeML, HeidelTime, timelines

       Contents

       List of Figures

       List of Tables

       Preface

       Acknowledgments

       1 Introduction

       1.1 The Task of Temporal Tagging

       1.2 Application Examples Exploiting Temporal Tagging

       1.3 Summary of the Chapter

       2 The Concept of Time

       2.1 Key Characteristics of Temporal Information

       2.2 Temporal Expressions in Documents

       2.3 Realizations of Temporal Expressions

       2.4 Summary of the Chapter

       3 Foundations of Temporal Tagging

       3.1 Annotation Standards

       3.2 Evaluating Temporal Taggers

       3.3 Research Competitions

       3.4 Annotated News-style Corpora

       3.5 Summary of the Chapter

       4 Domain-sensitive Temporal Tagging

       4.1 Temporal Tagging of News-style Documents

       4.2 The Concept of a Domain

       4.3 Annotated Non-news-style Corpora

       4.4 Characteristics of Different Domains

       4.4.1 News-style Documents

       4.4.2 Narrative-style Documents

       4.4.3 Colloquial-style Documents

       4.4.4 Autonomic-style Documents

       4.4.5 Further Domains and Summary

       4.5 Comparative Corpus Analysis—Challenges for Domain-sensitive Temporal Tagging

       4.6 Strategies for Domain-sensitive Temporal Tagging

       4.7 Summary of the Chapter

       5 Techniques and Tools

       5.1 Overview of Approaches to Temporal Tagging

       5.2 Overview of Existing Temporal Taggers

       5.2.1 TIPSem—Exploiting Semantic Information

       5.2.2 HeidelTime—Rule-based, Multilingual, Domain-sensitive

       5.2.3 SUTime—Rule-based, Stanford CoreNLP Component

       5.2.4 UWTime—Semantic Parsing of Time Expressions

       5.2.5 Comparison and Evaluation Results

       5.3 The Value of Domain-sensitive Temporal Tagging

       5.4 Approaches to Subtasks and Related Tasks

       5.5 Highly Multilingual Temporal Tagging

       5.6 Summary of the Chapter

       6 Summary and Future Research Directions

       6.1 Summary

       6.2 Future Directions