Integrated multi-strategic Web document pre-processing for sentence and word boundary detection

Information Processing and Management

Volumn 38, Issue 4, 2002, Pages 509-527

  Shim, Junhyeok ^a   Kim, Dongseok ^a   Cha, Jeongwon ^a   Geunbae Lee, Gary ^a   Seo, Jungyun ^b  

^a Pohang University of Science and Technology (POSTECH)   (South Korea)

^b Sogang University   (South Korea)

Author keywords

Sentence boundary disambiguation; Spacing word correction; Text normalization; Word boundary disambiguation

Indexed keywords

DECISION THEORY; HEURISTIC METHODS; HTML; HYPERTEXT SYSTEMS; LEARNING SYSTEMS; STATISTICAL METHODS;

INDUCTIVE LEARNING; TEXT NORMALIZATION;

WORLD WIDE WEB;

EID: 0036643016     PISSN: 03064573     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0306-4573(01)00044-9     Document Type: Article

References (14)

1. Automatic Korean spacing words correction system with bi-directional longest match strategy
2. What is a word, what is a sentence, problems of tokenisation
3. Automatic word-segmentation for Hangul sentences
4. A recognition of word spacing errors using syllable bi-gram
5. Morpheme-unit POS tagging model considering Eojeol-spacing
6. Three-stage word-spacing system for continuous syllable sentence in Korean
7. A knowledge-free method for capitalized word disambiguation
8. Document centered approach to text normalization
9. Adaptive multilingual sentence boundary disambiguation
10. A maximum entropy model for part-of-speech tagging
11. Some applications of tree-based modeling to speech and language indexing
12. Automated word-segmentation for Korean using mutual information of syllables