• Skip to primary navigation
  • Skip to content
  • Skip to footer
NAIST NLP Watanabe Lab
  • Members
  • Research
  • Publications
  • Software
  • Access
  • 日本語

    Software

    unsplash-logoChris Ried

    On this page

    • Software
      • NERsted
      • TorchLatent
      • Skeletal AMR
      • Tatar Transliteration
      • RemovingSpuriousAlignment
      • Coordparser

    Software

    NERsted

    A nested NER, which implements “Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path.”

    TorchLatent

    A library for efficient latent structure computation, e.g., CRF, used by “Structured Refinement for Sequential Labeling” and “Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path.”

    Skeletal AMR

    An AMR parser by dependency maching, which implements “Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing.”

    Tatar Transliteration

    A code-switching aware Tatar transliteraiton, which implements “Transliteration for Low-Resource Code-Switching Texts: Building an Automatic Cyrillic-to-Latin Converter for Tatar.” Please try an online demonstration.

    RemovingSpuriousAlignment

    An unsupervised image captioning, which implements “Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning.”

    Coordparser

    A coordinate structure parser based on neural networks implementing “Decomposed Local Models for Coordinate Structure Parsing.”

    • Twitter
    • GitHub
    © 2023 NAIST NLP: Natural Language Processing Laboratory (Watanabe Laboratory), Nara Institute of Science and Technology. Powered by Jekyll & Minimal Mistakes. Designed by Unsplash.