Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings.
Nikola LjubesicDarja FiserAnita Peti-StanticPublished in: CoRR (2018)
Keyphrases
- language specific
- n gram
- language independent
- compound words
- related words
- english words
- word segmentation
- word recognition
- word meaning
- arabic documents
- indian languages
- word pairs
- out of vocabulary
- word sense disambiguation
- unknown words
- character n grams
- cross lingual
- bilingual dictionaries
- word forms
- word order
- word frequencies
- word level
- word similarity
- multiword
- text corpus
- spoken document retrieval
- stop words
- word co occurrence
- natural language
- language model
- translation model
- statistical machine translation
- linguistic information
- machine translation
- syntactic categories
- parallel corpora
- training corpus
- pos taggers
- target language
- lexical information
- word meanings
- keywords
- arabic language
- chinese word segmentation
- word spotting
- co occurrence
- punctuation marks
- vector space
- lexical features
- parallel corpus
- linguistic knowledge
- english text
- grammar induction
- noun phrases
- word sense
- language identification
- cross language information retrieval
- handwritten words
- source language
- word alignment
- machine translation system
- natural language text
- spoken language
- automatic speech recognition
- distributional clustering
- speech recognition
- word frequency
- cross language
- part of speech
- query words
- text summarization