Unsupervised Contextualized Document Representation.
Ankur GuptaVivek GuptaPublished in: SustaiNLP@EMNLP (2021)
Keyphrases
- document representation
- bag of words
- document clustering
- document collections
- language model
- data fusion
- vector space model
- text documents
- document categorization
- vector space
- semantic information
- document content
- web documents
- unsupervised learning
- n gram
- image classification
- semi supervised
- text data
- probabilistic model
- information retrieval
- wordnet
- supervised learning
- multiscale
- feature extraction
- clustering algorithm
- multimedia
- metadata