Natural Language Processing (NLP) Tools

KyTea (cutie)

• Word segmentation
• Part-of-speech tagging
• Pronunciation estimation

N3ER(???)

• Named entity (word sequences with a class) recognizer
• New version of PWNER

This is based on a neural network (Bi-LSTM). We are improving this!

EDA (eda)

• Dependency parsing

PNAT (peanat)

• Corpus annotation
  • Word boundary
  • Part-of-speech and pronunciation of words
  • Named entity tag
  • Word dependency

CaPSL (capsule)

Kagamine Lin, Ren (kagamine lin, ren)

• Word sequence aquisition for a language model
• Word clustering for a language model

PALIN (palin, coming soon)

• Unknown word extraction (string, part-of-speech)
• Unknown named entity extraction (word sequence, named entity class)

?? (??, under construction)

• Named entity extraction

Twitter Demo