Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings.
Nikola LjubesicDarja FiserAnita Peti-StanticPublished in: Rep4NLP@ACL (2018)
Keyphrases
- language specific
- n gram
- language independent
- compound words
- related words
- word pairs
- english words
- word recognition
- word segmentation
- arabic documents
- word meaning
- indian languages
- word sense disambiguation
- bilingual dictionaries
- cross lingual
- word order
- word frequencies
- unknown words
- character n grams
- word meanings
- word level
- word forms
- target language
- multiword
- syntactic categories
- translation model
- parallel corpora
- out of vocabulary
- word spotting
- pos taggers
- linguistic information
- stop words
- chinese word segmentation
- natural language
- text corpus
- keywords
- machine translation
- linguistic knowledge
- word similarity
- statistical machine translation
- text classification
- word co occurrence
- english text
- noun phrases
- cross language information retrieval
- parallel corpus
- numeral strings
- arabic language
- vector space
- punctuation marks
- query translation
- handwritten words
- word alignment
- part of speech
- lexical features
- query words
- spoken document retrieval
- co occurrence
- language model
- machine translation system
- document images
- source language
- text summarization
- automatic transcription
- latent topics
- text documents
- word frequency
- pos tagging
- speech recognition systems
- text corpora