Dependency vs. Constituent Based Syntactic N-Grams in Text Similarity Measures for Paraphrase Recognition.
Hiram CalvoAndrea Segura-OlivaresAlejandro GarcíaPublished in: Computación y Sistemas (2014)
Keyphrases
- n gram
- word level
- recognizing textual entailment
- similarity measure
- language independent
- text classification
- character n grams
- language model
- document analysis
- bag of words
- language modeling
- variable length
- language specific
- web documents
- viterbi algorithm
- text documents
- text mining
- part of speech
- word recognition
- textual entailment
- semantic roles
- semantic similarity
- feature selection
- word segmentation
- text categorization
- text retrieval
- semantic representations
- natural language
- natural language text
- information retrieval
- sentence level
- character recognition
- document representation
- neural network
- query expansion
- knowledge discovery
- keywords
- data mining