Creating a Novel Geolocation Corpus from Historical Texts.
Grant DeLozierBenjamin WingJason BaldridgeScott NesbitPublished in: LAW@ACL (2016)
Keyphrases
- natural language text
- training corpus
- english words
- information extraction systems
- newspaper articles
- world knowledge
- historical data
- linguistic information
- writing style
- text corpus
- word sense
- manually annotated
- natural language generation
- linguistic patterns
- chinese texts
- textual features
- automatically generating
- statistical machine translation
- free text
- text documents
- supervised machine learning
- bag of words
- test set
- information extraction
- natural language
- keywords
- knowledge base
- machine learning
- data sets