HinFlair: pre-trained contextual string embeddings for pos tagging and text classification in the Hindi language.
Harsh PatelPublished in: CoRR (2021)
Keyphrases
- text classification
- pos tagging
- pre trained
- target language
- source language
- word segmentation
- machine translation
- part of speech
- named entity recognition
- n gram
- pos taggers
- bag of words
- text categorization
- natural language
- cross lingual
- text documents
- training data
- feature selection
- dependency parsing
- text mining
- machine learning
- labeled data
- contextual information
- vector space
- language modeling
- training examples
- language independent
- information extraction
- data mining
- natural language processing
- word sense disambiguation
- data analysis
- domain adaptation
- cross language
- statistical machine translation
- machine translation system
- control signals
- conditional random fields
- unlabeled data