Alternatives and similar repositories for RoBERTa-japanese:

Users that are interested in RoBERTa-japanese are comparing it to the libraries listed below

• kajyuuen / funer
  Funer is Rule based Named Entity Recognition tool.
  ☆22Updated 3 years ago
• yagays / pytorch_bert_japanese
  ☆35Updated 4 years ago
• yagays / swem
  Python implementation of SWEM (Simple Word-Embedding-based Methods)
  ☆29Updated 2 years ago
• yagays / nayose-wikipedia-ja
  Wikipediaから作成した日本語名寄せデータセット
  ☆35Updated 5 years ago
• hottolink / hottoSNS-bert
  hottoSNS-BERT: 大規模SNSコーパスによる文分散表現モデル
  ☆61Updated 5 months ago
• kajyuuen / daaja
  This repository has implementations of data augmentation for NLP for Japanese.
  ☆64Updated 2 years ago
• yagays / embedrank
  Python Implementation of EmbedRank
  ☆48Updated 6 years ago
• megagonlabs / jrte-corpus
  Japanese Realistic Textual Entailment Corpus (NLP 2020, LREC 2020)
  ☆76Updated last year
• cl-tohoku / JAQKET_baseline
  ☆16Updated 3 years ago
• tetsuwaka / CausalExtraction
  ☆20Updated 4 years ago
• WorksApplications / chikkarpy
  Japanese synonym library
  ☆53Updated 3 years ago
• akirakubo / bert-japanese-aozora
  Japanese BERT trained on Aozora Bunko and Wikipedia, pre-tokenized by MeCab with UniDic & SudachiPy
  ☆40Updated 4 years ago
• megagonlabs / UD_Japanese-GSD
  Japanese data from the Google UDT 2.0.
  ☆28Updated 2 years ago
• nobu-g / cohesion-analysis
  Code for COLING 2020 Paper
  ☆13Updated 3 weeks ago
• WorksApplications / SudachiTra
  Japanese tokenizer for Transformers
  ☆80Updated last year
• KodairaTomonori / ThreeLineSummaryDataset
  ☆30Updated 7 years ago
• tanreinama / Japanese-BPEEncoder
  Japanese-BPEEncoder
  ☆41Updated 3 years ago
• Katsumata420 / wikihow_japanese
  ☆36Updated 4 years ago
• nekoumei / DocumentClassificationUsingBERT-Japanese
  ☆40Updated 4 years ago
• megagonlabs / ginza-transformers
  Use custom tokenizers in spacy-transformers
  ☆16Updated 2 years ago
• ujiuji1259 / uke_japanese
  ☆13Updated 3 years ago
• p-geon / DropoutCheatSheet
  ☆33Updated 5 years ago
• sonoisa / t5-japanese
  日本語T5モデル
  ☆115Updated 7 months ago
• daac-tools / python-vaporetto
  🛥 Vaporetto is a fast and lightweight pointwise prediction based tokenizer. This is a Python wrapper for Vaporetto.
  ☆20Updated last month
• wwwcojp / ja_sentence_segmenter
  japanese sentence segmentation library for python
  ☆70Updated 2 years ago
• ken11 / bert-japanese-ner-finetuning
  ☆11Updated 2 years ago
• verypluming / JSICK
  Repository for JSICK
  ☆44Updated last year
• kanjirz50 / termextract
  専門用語抽出アルゴリズムの実装の練習
  ☆18Updated 6 years ago
• GENZITSU / UsefulMaterials
  ☆34Updated 5 years ago
• osekilab / JCoLA
  ☆18Updated 11 months ago