Distributional Word Representations for Code-mixed Text in Moroccan Darija.
Mohamed AghzalAsmaa MourhirPublished in: ACLING (2021)
Keyphrases
- co occurrence
- natural language text
- sentence level
- compressed text
- word counts
- word pairs
- keywords
- english text
- text corpus
- string matching
- text input
- linguistic information
- related words
- lexical features
- word co occurrence
- text mining
- source code
- printed text
- text segments
- syntactic categories
- english words
- word level
- stop words
- semantic representations
- page layout
- chinese text
- syntactic analysis
- information retrieval
- word clouds
- printed documents
- n gram
- unknown words
- sentence similarity
- lexical information
- text retrieval
- training corpus
- word sense disambiguation
- multiword
- cursive handwriting
- punctuation marks
- word frequency
- information extraction
- web documents
- word sense
- syntactic information
- text documents
- concept space
- word recognition
- word segmentation