Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader.

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references (pages 141-177).

1. Introduction -- 1.1 Information extraction -- 1.2 Ambiguity -- 1.3 Performance -- 1.4 Structure of the book --

2. Linguistic processing -- 2.1 Introduction -- 2.2 Approaches to linguistic processing -- 2.3 NLP pipelines -- 2.4 Tokenization -- 2.5 Sentence splitting -- 2.6 POS tagging -- 2.7 Morphological analysis and stemming -- 2.7.1 Stemming -- 2.8 Syntactic parsing -- 2.9 Chunking -- 2.10 Summary --

3. Named entity recognition and classification -- 3.1 Introduction -- 3.2 Types of named entities -- 3.3 Named entity evaluations and corpora -- 3.4 Challenges in NERC -- 3.5 Related tasks -- 3.6 Approaches to NERC -- 3.6.1 Rule-based approaches to NERC -- 3.6.2 Supervised learning methods for NERC -- 3.7 Tools for NERC -- 3.8 NERC on social media -- 3.9 Performance -- 3.10 Summary --

4. Relation extraction -- 4.1 Introduction -- 4.2 Relation extraction pipeline -- 4.3 Relationship between relation extraction and other IE tasks -- 4.4 The role of knowledge bases in relation extraction -- 4.5 Relation schemas -- 4.6 Relation extraction methods -- 4.6.1 Bootstrapping approaches -- 4.7 Rule-based approaches -- 4.8 Supervised approaches -- 4.9 Unsupervised approaches -- 4.10 Distant supervision approaches -- 4.10.1 Universal schemas -- 4.10.2 Hybrid approaches -- 4.11 Performance -- 4.12 Summary --

5. Entity linking -- 5.1 Named entity linking and semantic linking -- 5.2 NEL datasets -- 5.3 LOD-based approaches -- 5.3.1 DBpedia spotlight -- 5.3.2 YODIE: a LOD-based entity disambiguation framework -- 5.3.3 Other key LOD-based approaches -- 5.4 Commercial entity linking services -- 5.5 NEL for social media content -- 5.6 Discussion --

6. Automated ontology development -- 6.1 Introduction -- 6.2 Basic principles -- 6.3 Term extraction -- 6.3.1 Approaches using distributional knowledge -- 6.3.2 Approaches using contextual knowledge -- 6.4 Relation extraction -- 6.4.1 Clustering methods -- 6.4.2 Semantic relations -- 6.4.3 Lexico-syntactic patterns -- 6.4.4 Statistical techniques -- 6.5 Enriching ontologies -- 6.6 Ontology development tools -- 6.6.1 Text2Onto -- 6.6.2 SPRAT -- 6.6.3 FRED -- 6.6.4 Semi-automatic ontology creation -- 6.7 Summary --

7. Sentiment analysis -- 7.1 Introduction -- 7.2 Issues in opinion mining -- 7.3 Opinion-mining subtasks -- 7.3.1 Polarity recognition -- 7.3.2 Opinion target detection -- 7.3.3 Opinion holder detection -- 7.3.4 Sentiment aggregation -- 7.3.5 Further linguistic subcomponents -- 7.4 Emotion detection -- 7.5 Methods for opinion mining -- 7.6 Opinion mining and ontologies -- 7.7 Opinion-mining tools -- 7.8 Summary --

8. NLP for social media -- 8.1 Social media streams: characteristics, challenges, and opportunities -- 8.2 Ontologies for representing social media semantics -- 8.3 Semantic annotation of social media -- 8.3.1 Keyphrase extraction -- 8.3.2 Ontology-based entity recognition in social media -- 8.3.3 Event detection -- 8.3.4 Sentiment detection and opinion mining -- 8.3.5 Cross-media linking -- 8.3.6 Rumor analysis -- 8.3.7 Discussion --

9. Applications -- 9.1 Semantic search -- 9.1.1 What is semantic search? -- 9.1.2 Why semantic full-text search? -- 9.1.3 Semantic search queries -- 9.1.4 Relevance scoring and retrieval -- 9.1.5 Semantic search full-text platforms -- 9.1.6 Ontology-based faceted search -- 9.1.7 Form-based semantic search interfaces -- 9.1.8 Semantic search over social media streams -- 9.2 Semantic-based user modeling -- 9.2.1 Constructing social semantic user models from semantic annotations -- 9.2.2 Discussion -- 9.3 Filtering and recommendations for social media streams -- 9.4 Browsing and visualization of social media streams -- 9.5 Discussion and future work --

10. Conclusions -- 10.1 Summary -- 10.2 Future directions -- 10.2.1 Cross-media aggregation and multilinguality -- 10.2.2 Integration and background knowledge -- 10.2.3 Scalability and robustness -- 10.2.4 Evaluation, shared datasets, and crowdsourcing -- Bibliography -- Authors' biographies.

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

INSPEC

Google scholar

Google book search

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.

Also available in print.

Title from PDF title page (viewed on January 24, 2017).