ku-nlp Goto Github PK

abstractive-multi-video-captioning

The implementation of the paper "Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation."

abstracts

Benchmark dataset for abstractive multi-video captioning.

annotatedfkccorpus

Annotated Fuman Kaitori Center Corpus

arkitscenerefer

ARKitSceneRefer: Text-based Localization of Small Objects in Diverse Real-World 3D Indoor Scenes (EMNLP 2023 Findings)

bert

TensorFlow code and pre-trained models for BERT

bert-based-faqir

bertknp

A Japanese dependency parser based on BERT

chatcollectionframework

cner_wt-wf

covost2nativeja

Corpus for speech-to-text translation in Japanese-English based on CoVoST 2

detectblocks

dockerfile-jumanpp-knp

Dockerfiles for Juman++, KNP, and KWJA

east-meld

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

ishi

Ishi: A volition classifier for Japanese

ja-vicuna-qa-benchmark

jkusea

Utilitary tool aligning sentences of texts written in 2 different languages.

jmrd

Japanese Movie Recommendation Dialogue dataset

juman

jumandic

jumandic-grammar

grammar files and related scripts

jumandic-py

A Python API for JumanDIC.

jumanpp

Juman++ (a Morphological Analyzer Toolkit)

jumanpp-jumandic

Scripts for training Jumandic Juman++ model

knp

A Japanese Parser

knp2dcsvec

A tool to convert a KNP output to triples for DCSVec

kuci

Kyoto University Commonsense Inference dataset (KUCI)

kwdlc

Kyoto University Web Document Leads Corpus

kwja

An integrated Japanese analyzer based on foundation models

kyoto-reader

A processor for KyotoCorpus, KWDLC, and AnnotatedFKCCorpus