Specialized Document Embeddings for Aspect-based Similarity of Research Papers.
Malte OstendorffTill BlumeTerry RuasBela GippGeorg RehmPublished in: CoRR (2022)
Keyphrases
- document similarity
- special issue
- distance measure
- similarity measure
- cosine similarity
- document clustering
- vector space
- scientific papers
- web documents
- document images
- document collections
- retrieval systems
- content similarity
- document classification
- vector space model
- information retrieval
- euclidean distance
- cf loadingtexthtml
- general purpose
- binary codes
- information retrieval systems
- special section
- semantic similarity
- tf idf
- structured documents
- text representation
- document analysis
- document space
- dimensionality reduction
- similarity scores
- document retrieval
- low dimensional
- edit distance
- euclidean space
- text documents