Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval.
Shitao XiaoZheng LiuWeihao HanJianjin ZhangYingxia ShaoDefu LianChaozhuo LiHao SunDenvy DengLiangjie ZhangQi ZhangXing XiePublished in: WWW (2022)
Keyphrases
- document representation
- vector space
- index terms
- document content
- retrieval model
- bag of words
- document collections
- vector space model
- data fusion
- document retrieval
- web documents
- language model
- document clustering
- text documents
- semantic information
- information retrieval
- test collection
- retrieval systems
- information retrieval systems
- image retrieval
- text classification
- text data
- relevance feedback
- text mining
- language modeling
- information extraction
- knn
- query expansion