Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations.
Aditi ChaudharyChunting ZhouLori S. LevinGraham NeubigDavid R. MortensenJaime G. CarbonellPublished in: CoRR (2018)
Keyphrases
- n gram
- language independent
- word recognition
- word forms
- spoken document retrieval
- language specific
- character n grams
- english text
- out of vocabulary
- word segmentation
- grammar induction
- co occurrence
- vector space
- statistical machine translation
- target language
- expressive power
- intermediate representations
- compound words
- cross lingual
- indian languages
- multiscale
- multiword
- cross language
- manifold learning
- text classification
- language model
- dimensionality reduction
- word pairs
- broadcast news
- text summarization
- cross language information retrieval
- low dimensional
- syntactic categories
- keywords
- feature selection
- word clouds