Creating a contemporary corpus of similes in Serbian by using natural language processing.
Nikola MilosevicGoran NenadicPublished in: CoRR (2018)
Keyphrases
- natural language processing
- broad coverage
- reference resolution
- coreference resolution
- natural language
- text processing
- information extraction
- named entity recognition
- text mining
- manually annotated
- machine learning
- question answering
- computational linguistics
- wordnet
- knowledge representation
- computational biology
- language processing
- ontology learning
- spoken dialog
- free text
- word sense disambiguation
- semantic relations
- named entities
- artificial intelligence
- natural language text
- text summarization
- text corpora
- semantic analysis
- supervised machine learning
- open domain
- entity extraction