KornWtp / ConGenLinks
Implementation of ConGen: Unsupervised Control and Generalization Distillation For Sentence Representation (Finding of EMNLP 2022).
☆22Updated 2 years ago
Alternatives and similar repositories for ConGen
Users that are interested in ConGen are comparing it to the libraries listed below
Sorting:
- SCT: An Efficient Self-Supervised Cross-View Training For Sentence Embedding (TACL)☆16Updated last year
- A Multilingual Replicable Instruction-Following Model☆95Updated 2 years ago
- Pretraining transformer based Thai language models☆122Updated last year
- Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback☆97Updated 2 years ago
- Semantically Structured Sentence Embeddings☆67Updated 11 months ago
- Observe the slow deterioration of my mental sanity in the github commit history☆12Updated 2 years ago
- BERT pre-training in Thai language☆59Updated 6 years ago
- More than 43+ collections of Thai Natural Language Processing libraries. Update daily.☆30Updated 7 years ago
- Dataset from the paper "Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering" (COLING 2022)☆114Updated 2 years ago
- MAFAND-MT☆59Updated last year
- ☆15Updated 4 months ago
- ARCHIVED. Please use https://docs.adapterhub.ml/huggingface_hub.html || 🔌 A central repository collecting pre-trained adapter modules☆67Updated last year
- GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embeddings☆45Updated last year
- Benchmark for Thai sentence representation☆128Updated 4 months ago
- triple-encoders is a library for contextualizing distributed Sentence Transformers representations.☆15Updated last year
- WangChanGLM 🐘 - The Multilingual Instruction-Following Model☆95Updated last year
- Multilingual Entity Linking model by BELA model☆12Updated 2 years ago
- ☆41Updated 4 years ago
- ☆54Updated 2 years ago
- ☆68Updated 5 months ago
- Collection of NLP model explanations and accompanying analysis tools☆144Updated 2 years ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆79Updated 3 years ago
- Efficient Attention for Long Sequence Processing☆97Updated last year
- Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.☆105Updated 3 years ago
- This repository contains materials for the SIGIR 2022 tutorial on opinion summarization.☆34Updated 3 years ago
- ☆100Updated last year
- TimeLMs: Diachronic Language Models from Twitter☆111Updated last year
- ☆30Updated 3 years ago
- Code & Data for Comparative Opinion Summarization via Collaborative Decoding (Iso et al; Findings of ACL 2022)☆23Updated 7 months ago
- Official repository for our EACL 2023 paper "LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization" (https…☆44Updated last year