Kyoto Text Analysis Toolkit (KyTea)

A Kyoto Text Analysis Toolkit (KyTea) is a NLP Toolkit that can perform word segmentation and POS tagging tasks.

• AKA: KyTea.
• Context:
  • Website: http://www.phontron.com/kytea/
  • It is centered on Japanese and Chinese languages.
• Example(s):
  • kytea - source code,
  • …
• Counter-Example(s):
  • Kyoto Free Translation Task (KFTT).
  • MOSES,
  • SentencePiece.
• See: Neural Machine Translation Task, Subword Segmentation, Subword Unit, BLEU Score, Byte Pair Encoding (BPE), Subword Neural Machine Translation.

---

---

References

2021

• (KyTea) ⇒ http://www.phontron.com/kytea/ Retrieved:2021-02-14.
  • QUOTE: This is the home of the Kyoto Text Analysis Toolkit (KyTea, pronounced "cutie"). It is a general toolkit developed for analyzing text, with a focus on Japanese, Chinese and other languages requiring word or morpheme segmentation.

2011

• (Neubig et al., 2011) ⇒ Graham Neubig，Yosuke Nakata, and Shinsuke Mori (2011)．"Pointwise Prediction for Robust, Adaptable Japanese Morphological Analysis". In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT).

2010

• (Neubig & Mori, 2010) ⇒ Graham Neubig， and Shinsuke Mori (2010)． "Word-based Partial Annotation for Efficient Corpus Construction". In: Proceedings the seventh International Conference on Language Resources and Evaluation (LREC 2010).

---