PDF Ebook Natural Language Processing: A Human–Computer
Natural language processing has been in existence for more than fifty years. During this time, it has significantly contributed to the field of human-computer interaction in terms of theoretical results and practical applications. As computers continue to become more affordable and accessible, the importance of user interfaces that are effective, robust, unobtrusive, and user-friendly – regardless of user expertise or impediments – becomes more pronounced. Since natural language usually provides for effortless and effective communication in human-human interaction, its significance and potential in human-computer interaction should not be overlooked – either spoken or typewritten, it may effectively complement other available modalities,1 such as windows, icons, and menus, and pointing; in some cases, such as in users with disabilities, natural language may even be the only applicable modality. This chapter examines the field of natural language processing as it relates to human-computer interaction by focusing on its history, interactive application areas, theoretical approaches to linguistic modeling, and relevant computational and philosophical issues. It also presents a taxonomy for interactive natural language systems based on their linguistic knowledge and processing requirements, and reviews related applications. Finally, it discusses linguistic coverage issues, and explores the development of natural language widgets and their integration into multimodal user interfaces.
The field of natural language processing (NLP) originated approximately five decades ago with machine translation systems. In 1946, Warren Weaver and Andrew Donald Booth discussed the technical feasibility of machine translation “by means of the techniques developed during World War II for the breaking of enemy codes” (Booth and Locke, 1955, p. 2). During the more than fifty years of its existence, the field has evolved from the dictionary-based machine translation systems of the fifties to the more adaptable, robust, and user-friendly NLP environments of the nineties. This evolution has been marked by periods of considerable growth and funding “prosperity,” followed by years of intense criticism and lack of funding. This article attempts to provide an overview of this field by focusing on its history, current trends, some important theories and applications, and the state-of-the-art as it relates to human-computer interaction (HCI).
Contents
1. Introduction
1.1 Overview
1.2 Natural Language and User Interfaces
2. The Field of Natural Language Processing
2.1 An Extended Definition
2.2 Historical Background
3. Application Areas
3.1 Speech Understanding and Generation
3.2 Natural Language Interfaces.
1.1 Discourse Management, Story Understanding, and Text Generation
1.2 Interactive Machine Translation
1.3 Intelligent Writing Assistants
2. Linguistic Knowledge Models
2.1 Symbolic Approach
2.2 Stochastic Approach
2.3 Connectionist Approach
2.4 Hybrid Approach
3. Knowledge and Processing Requirements
3.1 Computational Issues
3.2 Understanding Natural Language
3.3 Natural Language Knowledge Levels
3.4 Classification of NLP Systems
3.5 Problem Areas
3.6 Linguistic Coverage
4. Multimodal Interaction
4.1 Effects of Natural Language on User Performance
4.2 Natural Language Widgets
4.3 Modality Integration
4.4 User Interface Management Systems
4.5 Development Methodologies
5. Conclusions
Acknowledgments
References
Download
PDF Ebook Natural Language Processing: A Human–Computer
Posted in :
