WorksApplications / chiVe
Japanese word embedding with Sudachi and NWJC 🌿
☆160Updated last year
Alternatives and similar repositories for chiVe:
Users that are interested in chiVe are comparing it to the libraries listed below
- Wikipediaを用いた日本語の固有表現抽出データセット☆136Updated last year
- Japanese text normalizer for mecab-neologd☆279Updated 2 weeks ago
- A lexicon for Sudachi☆245Updated 2 months ago
- A comparison tool of Japanese tokenizers☆121Updated 9 months ago
- 日本語WikipediaコーパスでBERTのPre-Trainedモデルを生成するためのリポジトリ☆115Updated 6 years ago
- おーぷん2ちゃんねるをクロールして作成した対話コーパス☆95Updated 3 years ago
- 自然言語で書かれた時間情報表現を抽出/規格化するルールベースの解析器☆139Updated last month
- A tool for dividing the Japanese full name into a family name and a given name.☆245Updated 2 weeks ago
- 日本語T5モデル☆115Updated 6 months ago
- Emotion analyzer for Japanese text☆115Updated 8 months ago
- chakki's Aspect-Based Sentiment Analysis dataset☆140Updated 3 years ago
- ☆97Updated last year
- Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)☆189Updated last year
- Japanese text8 corpus for word embedding.☆110Updated 7 years ago
- An integrated Japanese analyzer based on foundation models☆131Updated 6 months ago
- ☆160Updated 5 months ago
- 【2023年版】BERTによるテキスト分類☆233Updated 10 months ago
- A Python Module for JUMAN++/KNP