KornWtp / ConGen
Implementation of ConGen: Unsupervised Control and Generalization Distillation For Sentence Representation (Finding of EMNLP 2022).
☆21Updated last year
Related projects ⓘ
Alternatives and complementary repositories for ConGen
- WangchanX Fine-tuning Pipeline☆43Updated last month
- SCT: An Efficient Self-Supervised Cross-View Training For Sentence Embedding (TACL)☆14Updated 3 months ago
- The implementation of CL-ReLKT (NAACL-2022)☆13Updated 2 years ago
- Benchmark for Thai sentence representation☆102Updated 3 months ago
- Pytorch implementation of paper: Thai Nested Named Entity Recognition☆39Updated 3 weeks ago
- WangChanGLM 🐘 - The Multilingual Instruction-Following Model☆94Updated last year
- More than 43+ collections of Thai Natural Language Processing libraries. Update daily.☆21Updated 6 years ago
- Pretraining transformer based Thai language models☆119Updated last year
- Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation (ACL 2021 Findings).☆30Updated 9 months ago
- ☆37Updated 3 years ago
- Thai News Dataset from Thai government website.☆13Updated this week
- Thai text classification benchmarks☆36Updated 4 years ago
- English-Thai Machine Translation Models☆28Updated 6 months ago
- Thai Named Entity Recognition☆53Updated last year
- Thai sentence segmentation with conditional random fields☆15Updated 5 months ago
- Domain Adaptation of Thai Word Segmentation Models using Stacked Ensemble (EMNLP2020)☆20Updated 9 months ago
- BERT pre-training in Thai language☆60Updated 5 years ago
- ☆33Updated 6 months ago
- ShanNLP experimental project inspired by PythaiNLP☆10Updated last month
- ☆24Updated 11 months ago
- A Dataset for Thai Text Summarization with over 310K articles.☆28Updated last year
- ☆11Updated 11 months ago
- Thai Spelling Check☆36Updated last year
- Fix Thai PDF☆28Updated 8 months ago
- scripts for cleaning and creating train/validation/test splits for Thai commonvoice☆10Updated 3 years ago
- WorldCuisines is an extensive multilingual and multicultural benchmark that spans 30 languages, covering a wide array of global cuisines.☆12Updated 3 weeks ago
- ☆9Updated last year
- Thai Named Entity Recognition with BiLSTM-CRF using Word/Character Embedding☆16Updated 5 years ago
- A Dataset for Thai text summarization from Thairath, ThaiPBS, Prachathai and The Standard with over 350,000 articles. Trained models are …☆41Updated 6 months ago
- Dataset for fake news detection in healthcare domain☆12Updated 2 years ago