Text Classification Using Multilingual Sentence Embeddings.
Anant SaraswatKumar AbhishekSheshank KumarPublished in: FICTA (1) (2020)
Keyphrases
- text classification
- cross lingual
- language independent
- linguistic features
- training corpus
- parallel corpus
- text representation
- text generation
- n gram
- text categorization
- text mining
- sentence level
- sentiment classification
- bag of words
- sentiment analysis
- part of speech
- feature selection
- vector space
- low dimensional
- natural language
- labeled data
- cross language
- text documents
- naive bayes
- dimensionality reduction
- manifold learning
- machine learning
- text summarization
- text classifiers
- data cleaning
- euclidean space
- knn
- high dimensional data
- term frequency
- query translation
- semantic features
- image classification
- distance measure
- semi supervised
- knowledge discovery