Pinned Repositories
bert-based-faqir
ja-vicuna-qa-benchmark
JMRD
Japanese Movie Recommendation Dialogue dataset
jumanpp
Juman++ (a Morphological Analyzer Toolkit)
knp
A Japanese Parser
KWDLC
Kyoto University Web Document Leads Corpus
kwja
An integrated Japanese analyzer based on foundation models
KyotoCorpus
Kyoto University Text Corpus
pyknp
A Python Module for JUMAN++/KNP
rhoknp
Yet another Python binding for Juman++/KNP/KWJA
Language Media Processing Lab, Kyoto University's Repositories
ku-nlp/jumanpp
Juman++ (a Morphological Analyzer Toolkit)
ku-nlp/kwja
An integrated Japanese analyzer based on foundation models
ku-nlp/pyknp
A Python Module for JUMAN++/KNP
ku-nlp/KWDLC
Kyoto University Web Document Leads Corpus
ku-nlp/KyotoCorpus
Kyoto University Text Corpus
ku-nlp/ja-vicuna-qa-benchmark
ku-nlp/rhoknp
Yet another Python binding for Juman++/KNP/KWJA
ku-nlp/knp
A Japanese Parser
ku-nlp/bertknp
A Japanese dependency parser based on BERT
ku-nlp/AnnotatedFKCCorpus
Annotated Fuman Kaitori Center Corpus
ku-nlp/text-cleaning
A powerful text cleaner for Japanese web texts
ku-nlp/WikipediaAnnotatedCorpus
ku-nlp/kyoto-reader
A processor for KyotoCorpus, KWDLC, and AnnotatedFKCCorpus
ku-nlp/pyknp-eventgraph
ku-nlp/KyotoCorpusAnnotationTool
An annotation tool for the Kyoto University Corpus
ku-nlp/KUCI
Kyoto University Commonsense Inference dataset (KUCI)
ku-nlp/dockerfile-jumanpp-knp
Dockerfiles for Juman++, KNP, and KWJA
ku-nlp/speechBSD
An extension of the BSD corpus with audio and speaker attribute information
ku-nlp/video-helpful-MMT
ku-nlp/RecomMind
Movie recommendation dialogue dataset with first- and second-person annotations of the seeker’s internal state at the entity level.
ku-nlp/sdg4idrr
Synthetic Data Generation for Implicit Discourse Relation Recognition (SDG4IDRR)
ku-nlp/EaST-MELD
ku-nlp/SMD4FVG
Flexible Visual Grounding
ku-nlp/Abstractive-Multi-Video-Captioning
The implementation of the paper "Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation."
ku-nlp/AbstrActs
Benchmark dataset for abstractive multi-video captioning.
ku-nlp/ARKitSceneRefer
ARKitSceneRefer: Text-based Localization of Small Objects in Diverse Real-World 3D Indoor Scenes (EMNLP 2023 Findings)
ku-nlp/CNER_WT-WF
ku-nlp/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
ku-nlp/JumanDIC-py
A Python API for JumanDIC.
ku-nlp/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.