On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi.
Harsh ChaudhariAnuja PatilDhanashree LavekarPranav KhairnarRaviraj JoshiSachin PandePublished in: CoRR (2023)
Keyphrases
- named entity recognition
- named entities
- information extraction
- natural language processing
- out of vocabulary
- text summarization
- conditional random fields
- maximum entropy
- annotated corpus
- co occurrence
- chinese named entity recognition
- proper names
- sequence labeling
- question answering
- semi supervised
- relation extraction
- image retrieval
- image processing
- learning algorithm
- machine learning