
A script for learning word embedding models such as word2vec, fastText, and GloVe based on the results of morphological analysis using both the IPA dictionary and the latest Neologd dictionary, using MeCab on the latest Japanese Wikipedia dump data.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
12
+1 (Oct 13〜)
Last commit
May 2020
Created on GitHub
Feb 13, 2019
Listed
Aug 9, 2022
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 11 |
| Jan 2026 | 11 |
| Feb 2026 | 11 |
| Mar 2026 | 11 |
| Apr 2026 | 11 |
| May 2026 | 11 |
| Jun 2026 | 11 |
| Jul 2026 | 11 |
| Aug 2026 | 11 |
| Sep 2026 | 11 |
| Oct 2026 | 12 |
| Nov 2026 | 12 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
chiVeWorksApplications179Japanese word embedding with Sudachi and NWJC
dependency-based-japanese-word-embeddingslapras-inc8This is a repository for the AI LAB article "係り受けに基づく日本語単語埋込 (Dependency-based Japanese Word Embeddings)" ( Article URL https://ai-lab.lapras.com/nlp/japanese-word-embedding/)
japanese-words-to-vectorsphilipperemy87Word2vec (word to vectors) approach for Japanese language using Gensim and Mecab.
embedrankyagays48Python Implementation of EmbedRank
elmo-japanesecl-tohoku4Elmo (in Japanese)
aoveceggplants3Easy aozorabunko Word2Vec Builder - Word2Vec Builder and pre-built model for all books in the Aozora Bunko library.
Resources in similar research fields
jglue-evaluation-scriptsnobu-g18About Training and evaluation scripts for JGLUE, a Japanese language understanding benchmarkShared: Annotation and Dataset Development
jqarahotchpotch45JQaRA: Japanese Question Answering with Retrieval Augmentation - 検索拡張(RAG)評価のための日本語Q&AデータセットShared: Annotation and Dataset Development
selective-rag-kasensabotk-yasuno1This is a practical Agentic RAG system MVP that accurately automatically determines the expertise granularity (fine/coarse) of questions related to construction technology standards at 96% and selects the optimal RAG system (ColBERT/Naive). Four RAG systems were built targeting the technical standards of river sand control dams published in November 2025, and accuracy and speed were compared for 200 questions with different granularity of expertise.Shared: Annotation and Dataset Development- RAG-Evaluation-Dataset-JAallganize246Provides a Japanese RAG benchmark across five industry domains—finance, telecom, manufacturing, public, retail—by publishing datasets, an automatic evaluation framework, and comparative results for models such as Claude 3.5‑Sonnet, GPT‑4o, and others.HF datasetShared: Annotation and Dataset Development
- Japanese-RAG-Generator-Benchmarkneoai-inc113Japanese RAG Generator Benchmark (J‑RAGBench) supplies a multi‑category QA dataset—covering Integration, Reasoning, Logical, Table, and Abstention—designed to evaluate Japanese RAG generators, built with human effort and GPT‑4.1, and released under CC BY‑SA 4.0.HF datasetShared: Annotation and Dataset Development
- emilia-yodasTTS-AGI18kDataset of dialogues and lore from the Fate/Stay Night character “Emilia”, formatted for training and evaluating conversational language models.HF datasetShared: Annotation and Dataset Development