shimo-lab / Universal-Geometry-with-ICALinks
Discovering Universal Geometry in Embeddings with ICA (Published in EMNLP 2023)
☆18Updated last week
Alternatives and similar repositories for Universal-Geometry-with-ICA
Users that are interested in Universal-Geometry-with-ICA are comparing it to the libraries listed below
Sorting:
- Capturing Set-Theoretic Semantics of Words using Box Embeddings☆35Updated 2 years ago
- Repository of ACL2023 paper: Unbalanced Optimal Transport for Unbalanced Word Alignment☆38Updated last year
- ☆16Updated 6 months ago
- ☆27Updated last month
- DIRECT: Direct and Indirect REsponses in Conversational Text Corpus☆16Updated 3 years ago
- 日本語マルチタスク言語理解ベンチマーク Japanese Massive Multitask Language Understanding Benchmark☆36Updated 5 months ago
- ☆17Updated 2 years ago
- ☆33Updated 10 months ago
- A library for semantic similarity search☆24Updated 4 months ago
- ☆9Updated 2 years ago
- DefSent: Sentence Embeddings using Definition Sentences☆20Updated 3 years ago
- A simple implementation of SimCSE☆77Updated 2 years ago
- ☆19Updated last year
- Japanese semantic test suite (FraCaS counterpart and extensions)☆13Updated 7 months ago
- ☆11Updated last week
- Swallowプロジェクト 大規模言語モデル 評価スクリプト☆17Updated last month
- ☆46Updated 2 years ago
- LEIA: Facilitating Cross-Lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation☆21Updated last year
- ☆26Updated 7 months ago
- Utility scripts for preprocessing Wikipedia texts for NLP☆77Updated last year
- https://www.nlp.ecei.tohoku.ac.jp/projects/aio/☆16Updated 2 years ago
- Yet another Python binding for Juman++/KNP/KWJA☆32Updated this week
- Box Embeddings as Modules☆102Updated 2 years ago
- Code to train Sentence BERT Japanese model for Hugging Face Model Hub☆11Updated 3 years ago
- Repository for JSICK☆44Updated 2 years ago
- Funer is Rule based Named Entity Recognition tool.☆22Updated 3 years ago
- Use custom tokenizers in spacy-transformers☆16Updated 2 years ago
- ☆10Updated 2 years ago
- Training and evaluation scripts for JGLUE, a Japanese language understanding benchmark☆17Updated this week
- 🛥 Vaporetto is a fast and lightweight pointwise prediction based tokenizer. This is a Python wrapper for Vaporetto.☆20Updated this week