yukiar / OTAlign
Repository of ACL2023 paper: Unbalanced Optimal Transport for Unbalanced Word Alignment
☆36Updated last year
Related projects ⓘ
Alternatives and complementary repositories for OTAlign
- ☆25Updated 5 months ago
- Utility scripts for preprocessing Wikipedia texts for NLP☆76Updated 7 months ago
- DIRECT: Direct and Indirect REsponses in Conversational Text Corpus☆16Updated 3 years ago
- Yet another Python binding for Juman++/KNP/KWJA☆31Updated last month
- COMET-ATOMIC ja☆28Updated 8 months ago
- Code for COLING 2020 Paper☆13Updated 2 weeks ago
- ☆24Updated 2 weeks ago
- RealPersonaChat: A Realistic Persona Chat Corpus with Interlocutors' Own Personalities☆48Updated 8 months ago
- ☆18Updated last year
- Codes to pre-train Japanese T5 models☆40Updated 3 years ago
- ☆9Updated last year
- Capturing Set-Theoretic Semantics of Words using Box Embeddings☆34Updated 2 years ago
- ☆18Updated 5 months 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☆25Updated 8 months ago
- Flexible evaluation tool for language models☆36Updated this week
- A library for semantic similarity search☆23Updated 2 months ago
- NTT様の日本語版ペルソナチャットから本家ペルソナチャットのフォーマットに変換するプログラム☆8Updated last year
- Funer is Rule based Named Entity Recognition tool.☆22Updated 2 years ago
- A processor for KyotoCorpus, KWDLC, and AnnotatedFKCCorpus☆10Updated 4 months ago
- Repository for JSICK☆44Updated last year
- This repository has implementations of data augmentation for NLP for Japanese.☆64Updated last year
- ☆30Updated 6 years ago
- ☆11Updated 2 months ago
- 敬語変換タスクにおける評価用データセット☆20Updated last year
- ☆33Updated 3 months ago
- Wikipediaから作成した日本語名寄せデータセット☆34Updated 4 years ago
- Pytorch implementation and pre-trained Japanese model for CANINE, the efficient character-level transformer.☆90Updated last year
- The robust text processing pipeline framework enabling customizable, efficient, and metric-logged text preprocessing.☆118Updated 3 weeks ago
- Japanese tokenizer for Transformers☆78Updated 11 months ago
- Japanese data from the Google UDT 2.0.☆28Updated last year