kamigaito Goto Github PK

acl2021kge

allennlp-tagger

This repository has a sequential tagger implemented on AllenNLP. It can work in Japanese by default.

cfg_lexicalizer

"cfg_lexicalizer" can convert s-expressed trees to normalized ones, described in the paper ''Grammar as a Foreign Language.'' by Vinyals et al., In Proc of ICLR2015.

icml2022

jawiki_word_vector_updater

最新の日本語Wikipediaのダンプデータから，MeCabを用いてIPA辞書と最新のNeologd辞書の両方で形態素解析を実施し，その結果に基づいた word2vec，fastText，GloVeの単語分散表現を学習するためのスクリプト

mnist_examples

mnist_examples_cpu

https://github.com/HirokiNakahara/MNIST_Examples のCPU実行版

naist_lecture_mt

nlp-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

ptbconv-3.0

This ptbconv-3.0 can work on Ruby-1.9.3. Original ptbconv-3.0 is located on http://www.jaist.ac.jp/~h-yamada/

rf4wpc

This code can extract category links between titles in the xml formatted wikipedia dump file and retrofit word vectors based on these links.

rnnlm-pytorch

RNN-based language models in pytorch

seq2seq-baseline-dynet

slahan

SLAHAN is an implementation of Kamigaito et al., 2020, "Syntactically Look-A-Head Attention Network for Sentence Compression", In Proc. of AAAI2020.

tga-egliteracy-seq2seq

wikitig

Code for our paper, "Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models".