Aligning Word Vectors on Low-Resource Languages with Wiktionary.
Mike IzbickiPublished in: LoResMT@COLING (2022)
Keyphrases
- computing semantic relatedness
- resource allocation
- expressive power
- statistical machine translation
- language independent
- english text
- co occurrence
- n gram
- vector space
- target language
- feature vectors
- language specific
- image registration
- compound words
- indian languages
- word order
- resource management
- source language
- machine translation system
- cross lingual
- grammar induction
- word recognition
- word segmentation
- character n grams
- pos taggers
- text classification