Named entities for computational linguistics / Damien Nouvel, Maud Ehrmann, Sophie Rosset.

Format:

Book

Author/Creator:

Nouvel, Damien, author.

Ehrmann, Maud, author.

Rosset, Sophie, author.

Language:

English

Subjects (All):

Computational linguistics--Research.

Computational linguistics.

Physical Description:

1 online resource (187 p.)

Edition:

1st ed.

Place of Publication:

London, England ; Hoboken, New Jersey : ISTE Ltd : Wiley, 2016.

Summary:

One of the challenges brought on by the digital revolution of the recent decades is the mechanism by which information carried by texts can be extracted in order to access its contents. The processing of named entities remains a very active area of research, which plays a central role in natural language processing technologies and their applications. Named entity recognition, a tool used in information extraction tasks, focuses on recognizing small pieces of information in order to extract information on a larger scale. The authors use written text and examples in French and English to present the necessary elements for the readers to familiarize themselves with the main concepts related to named entities and to discover the problems associated with them, as well as the methods available in practice for solving these issues.-- Source other than Library of Congress.

Contents:

Cover

Title Page

Copyright

Contents

Introduction

Chapter 1: Named Entities for Accessing Information

1.1. Research program history

1.1.1. Understanding documents: an ambitious task

1.1.2. Detecting basic elements: named entities

1.1.3. Trend: a return to slot filling

1.2. Task using named entities as a basic representation

1.3. Conclusion

Chapter 2: Named Entities, Referential Units

2.1. Issues with the named entity concept

2.1.1. A heterogeneous set

2.1.1.1. Category multiplicity

2.1.1.2. Mention diversity

2.1.2. Existing defining formulas

2.1.3. An NLP object

2.2. The notions of meaning and reference

2.2.1. What is the reference?

2.2.2. What is meaning?

2.3. Proper names

2.3.1. The traditional criteria for defining a proper name

2.3.2. Meaning and referential function of proper names

2.3.3. The "referential load" of proper names

2.4. Definite descriptions

2.4.1. What is a definite description?

2.4.2. The meaning of definite descriptions

2.4.3. Complete and incomplete definite descriptions

2.5. The meaning and referential functioning of named entities

2.5.1. Reference to a particular

2.5.1.1. The principle of individuation

2.5.1.2. Referential uniqueness

2.5.2. Referential autonomy

2.5.3. A "natural" heterogeneity

2.6. Conclusion

Chapter 3: Resources Associated with Named Entities

3.1. Typologies: general and specialist domains

3.1.1. The notion of category

3.1.2. Typology development

3.1.3. Typologies beyond evaluation campaigns

3.1.4. Typologies beyond evaluation campaigns

3.1.5. Illustrated comparison

3.1.6. Issues to consider regarding entities

3.2. Corpora

3.2.1. Introduction

3.2.2. Corpora and named entities

3.2.2.1. MUC and ACE corpora

3.2.2.2. Corpora produced by French-language campaigns.

3.2.2.3. Corpus produced by the GermEval campaign

3.2.2.4. Corpus produced by the Evalita campaign

3.2.2.5. Corpus produced by the Harem campaign

3.2.3. Conclusion

3.3. Lexicons and knowledge databases

3.3.1. Lexical databases

3.3.1.1. ANNIE

3.3.1.2. WordNet

3.3.1.3. Prolex

3.3.1.4. Geonames

3.3.1.5. JRC-Names

3.3.1.6. The biomedical domain

3.3.1.7. Conclusion

3.3.2. Knowledge databases

3.4. Conclusion

Chapter 4: Recognizing Named Entities

4.1. Detection and classification of named entities

4.2. Indicators for named entity recognition

4.2.1. Describing word morphology

4.2.2. Using lexical databases

4.2.3. Contextual clues

4.2.4. Conclusion

4.3. Rule-based techniques

4.4. Data-driven and machine-learning systems

4.4.1. Majority class models

4.4.2. Contextual models (HMM)

4.4.3. Multiple feature models (Softmax and MaxEnt)

4.4.4. Conditional Random Fields (CRFs)

4.5. Unsupervised enrichment of supervised methods

4.6. Conclusion

Chpater 5: Linking Named Entities to References

5.1. Knowledge bases

5.2. Formalizing polysemy in named entity mentions

5.3. Stages in the named entity linking process

5.3.1. Detecting mentions of named entities

5.3.2. Selecting candidates for each mention

5.3.3. Entity disambiguation

5.3.4. Entity linking

5.4. System performance

5.4.1. Practical application: DBpedia Spotlight

5.4.2. Future prospects

Chapter 6: Evaluating Named Entity Recognition

6.1. Classic measurements: precision, recall and F-measures

6.2. Measures using error counts

6.3. Evaluating associated tasks

6.3.1. Detecting entities and mentions

6.3.2. Entity detection and linking

6.4. Evaluating preprocessing technologies

6.5. Conclusion

Conclusion

Appendices

Appendix 1: Glossary.

Appendix 2: Named Entities: Research Programs

Appendix 3: Summary of Available Corpora

Appendix 4: Annotation Formats

Appendix 5: Named Entities: Current Definitions

Bibliography

Index.

Notes:

Description based upon print version of record.

Includes bibliographical references and index.

Description based on print version record.

ISBN:

9781119268581

1119268583

9781119268574

1119268575

OCLC:

934770335