Labratory Project

Japanese Dependency Parsing

Japanese dependency parsing on conversational data using a dependency treebank of the CEJC.
PythonNLPDeep LearningPytorchJapanese
Japanese Dependency Parsing example
Work in Progress
This page is still under construction.

Corpus of Everyday Japanese Conversation (CEJC)

The transition-based model of [1] has been implemented and I attempted to implement the graph-based model in [1] and [2] as well.

References

  • [1] Kiperwasser, Eliyahu, and Yoav Goldberg. "Simple and accurate dependency parsing using bidirectional LSTM feature representations." Transactions of the Association for Computational Linguistics 4 (2016): 313-327.
  • [2] Dozat, Timothy, and Christopher D. Manning. "Deep biaffine attention for neural dependency parsing." arXiv preprint arXiv:1611.01734 (2016).