Unsupervised Document Embedding via Contrastive Augmentation.
Dongsheng LuoWei ChengJingchao NiWenchao YuXuchao ZhangBo ZongYanchi LiuZhengzhang ChenDongjin SongHaifeng ChenXiang ZhangPublished in: CoRR (2021)
Keyphrases
- information retrieval systems
- web documents
- document clustering
- data driven
- keywords
- document collections
- text documents
- document classification
- unsupervised learning
- retrieval systems
- unsupervised manner
- information retrieval
- semi supervised
- supervised learning
- document images
- machine learning
- database
- relevant documents
- user queries
- document retrieval
- digital libraries
- similarity measure
- text summarization
- topic modeling
- data hiding
- structured documents
- data embedding
- electronic documents