Semantic Text Matching for Long-Form Documents.
Jyun-Yu JiangMingyang ZhangCheng LiMichael BenderskyNadav GolbandiMarc NajorkPublished in: WWW (2019)
Keyphrases
- linguistic analysis
- semantic information
- arabic text
- semantic content
- document content
- information retrieval
- text documents
- automatic text
- sentence similarity
- machine readable form
- natural language text
- semantically related
- digital documents
- keywords
- semantic structure
- linguistic information
- semantic representation
- free text
- text representation
- web documents
- unstructured documents
- text retrieval
- latent semantic analysis
- document analysis
- semantic network
- plagiarism detection
- semantic relationships
- text collections
- document collections
- concept space
- textual content
- multimedia documents
- text information
- semantic similarity
- word frequency
- shallow semantic
- semantic representations
- document categorization
- information retrieval systems
- text mining
- related documents
- printed documents
- electronic documents
- text content
- string matching
- document level
- natural language
- xml documents
- semantic features
- textual data
- relevant documents
- metadata
- co occurrence
- query expansion
- semantic web
- document retrieval
- news stories
- multiword
- word pairs
- text categorization
- document set
- multi document summarization
- language model
- textual descriptions
- text corpus