A Japanese Corpus of Many Specialized Domains for Word Segmentation and Part-of-Speech Tagging.
Shohei HigashiyamaMasao IdeuchiMasao UtiyamaYoshiaki OidaEiichiro SumitaPublished in: Eval4NLP (2022)
Keyphrases
- word segmentation
- pos tagging
- chinese word segmentation
- n gram
- part of speech
- word recognition
- handwriting recognition
- dependency parsing
- topic tracking
- language independent
- text classification
- document analysis
- chinese text retrieval
- chinese text
- cross domain
- language modeling
- machine translation
- language model
- domain adaptation
- target domain
- cross lingual
- news articles
- transfer learning
- natural language processing