Natural language processing for historical texts /
| Main Author: | |
|---|---|
| Format: | eBook |
| Language: | English |
| Published: |
[San Rafael, Calif.] :
Morgan & Claypool,
[2012]
|
| Series: | Synthesis lectures on human language technologies ;
#17. |
| Subjects: | |
| Online Access: | Connect to the full text of this electronic book |
Table of Contents:
- 1. Introduction
- 1.1 Historical languages and modern languages
- 1.2 Intended audience
- 1.3 Outline
- 2. NLP and digital humanities
- 2.1 Origins of digital humanities
- 2.2 Convergence of NLP and digital humanities
- 2.3 Summary
- 3. Spelling in historical texts
- 3.1 The role of orthography in NLP
- 3.2 Spelling and historical texts
- 3.3 Summary
- 4. Acquiring historical texts
- 4.1 Digitization of historical texts
- 4.2 Scanning
- 4.3 Optical character recognition
- 4.4 Manual text entry
- 4.5 Computer-assisted transcription
- 4.6 Summary
- 5. Text encoding and annotation schemes
- 5.1 Unicode for historical text
- 5.2 TEI for historical texts
- 5.3 Summary
- 6. Handling spelling variation
- 6.1 Spelling canonicalization
- 6.2 Edit distance
- 6.3 Approaches for handling spelling variation in historical texts
- 6.4 Detecting and correcting OCR errors
- 6.5 Limits of spelling canonicalization
- 6.6 Summary
- 7. NLP tools for historical languages
- 7.1 Part-of-speech tagging
- 7.2 Lemmatization and morphological analysis
- 7.3 Syntactic parsing
- 7.4 Summary
- 8. Historical corpora
- 8.1 Arabic
- 8.2 Chinese
- 8.3 Dutch
- 8.4 English
- 8.5 French
- 8.6 German
- 8.7 Nordic languages
- 8.8 Latin and ancient Greek
- 8.9 Portuguese
- 8.10 Summary
- 9. Conclusion
- Bibliography
- Author's biography.