New Word Analogy Corpus for Exploring Embeddings of Czech Words.
Lukás SvobodaTomás BrychcínPublished in: CICLing (1) (2016)
Keyphrases
- english words
- word frequencies
- unknown words
- word pairs
- multiword
- text corpus
- linguistic information
- word co occurrence
- word sense
- language independent
- n gram
- training corpus
- related words
- parallel corpus
- lexical features
- word segmentation
- noun modifier
- noun phrases
- co occurrence
- word frequency
- spontaneous speech
- word sense disambiguation
- text corpora
- word meaning
- pos tagging
- word recognition
- chinese word segmentation
- semantic relations
- text classification
- language model
- ambiguous words
- parallel corpora
- part of speech
- natural language text
- conversational speech
- keywords
- information retrieval
- keyword extraction
- word spotting
- vector space
- semantic similarity
- sentence level
- handwritten words
- wordnet
- word similarity
- world knowledge
- bilingual dictionaries
- information extraction
- statistical machine translation
- automatic transcription