Text Similarity Using Word Embeddings to Classify Misinformation.
Caio Sacramento de Britto AlmeidaDébora Abdalla SantosPublished in: DHandNLP@PROPOR (2020)
Keyphrases
- sentence similarity
- word pairs
- semantic similarity
- concept space
- keywords
- sentence level
- word similarity
- text corpus
- natural language text
- text input
- english text
- string matching
- distance measure
- similarity measure
- text queries
- lexical features
- text segments
- text mining
- english words
- co occurrence
- linguistic information
- vector space
- text documents
- printed text
- word counts
- chinese text
- information retrieval
- named entity recognizer
- text representation
- printed documents
- dimensionality reduction
- syntactic information
- related words
- sentiment analysis
- text categorization
- text retrieval
- word level
- handwritten documents
- wordnet
- spoken documents
- semantic information
- document analysis
- edit distance
- n gram
- distance function
- noun phrases
- page layout
- syntactic categories
- punctuation marks
- word sense
- binary codes
- document collections
- multiword
- low dimensional
- euclidean distance