People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts.
Vít NovotnýKristýna LugerMichal StefánikTereza VrabcováAles HorákPublished in: CoRR (2023)
Keyphrases
- annotated corpus
- named entities
- named entity recognition
- relation extraction
- genia corpus
- information extraction
- natural language text
- text documents
- linguistic features
- text corpus
- natural language processing
- co occurrence
- weakly supervised
- named entity extraction
- text mining
- question answering
- natural language
- text summarization
- news corpus
- noun phrases
- keywords
- person names
- unsupervised learning
- automatic annotation
- coreference resolution
- semantic classes
- semi supervised
- conditional random fields
- maximum entropy
- pairwise
- automatic extraction
- word sense
- contextual features
- semantic relations