Multilingual Vector Representations of Words, Sentences, and Documents.
Gerard de MeloPublished in: IJCNLP (Tutorial Abstracts) (2017)
Keyphrases
- word frequency
- text corpus
- document representation
- multilingual documents
- multiword
- vector representation
- text documents
- document level
- linguistic analysis
- parallel corpus
- multi document summarization
- word spotting
- related words
- word alignment
- document collections
- keyphrases
- syntactic information
- sentence level
- automatic summarization
- text corpora
- extractive summarization
- keywords
- document summarization
- word pairs
- arabic language
- text segments
- cross lingual
- training corpus
- document clustering
- information retrieval
- sentence similarity
- noun phrases
- machine translation
- indian languages
- vector space
- document retrieval
- natural language
- word sense
- n gram
- text mining
- sentiment analysis
- source language
- word sense disambiguation
- bilingual dictionaries
- digital libraries
- language specific
- language independent
- cross language
- text generation
- related documents
- cross language information retrieval
- natural language processing
- named entities
- relevant documents
- document set
- text summarization
- vector space model
- information extraction
- question answering
- semantic information
- lexical chains
- semantic roles
- latent topics