Unsupervised word segmentation and lexicon discovery using acoustic word embeddings.
Herman KamperAren JansenSharon GoldwaterPublished in: CoRR (2016)
Keyphrases
- word segmentation
- pos tagging
- chinese text retrieval
- word recognition
- n gram
- handwritten words
- chinese word segmentation
- handwriting recognition
- unknown words
- language independent
- text classification
- word level
- chinese text
- semi supervised
- language modeling
- document analysis
- knowledge discovery
- lexical semantics
- supervised learning
- handwritten documents
- cross lingual
- pattern recognition
- historical documents
- low dimensional
- data mining