voidism / DiffCSE
Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"
☆290Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for DiffCSE
- ☆293Updated last year
- Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations☆133Updated 5 months ago
- [NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation☆466Updated 8 months ago
- PromptBERT: Improving BERT Sentence Embeddings with Prompts☆332Updated 11 months ago
- [NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining☆118Updated last year
- [EMNLP 2021] Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification☆125Updated last year
- Code for "Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (EMNLP 2022)"☆135Updated 11 months ago
- ICML'2022: NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework☆257Updated 10 months ago
- ☆155Updated 3 months ago
- EMNLP 2021 - Pre-training architectures for dense retrieval☆244Updated 2 years ago
- Code associated with the Don't Stop Pretraining ACL 2020 paper☆525Updated 2 years ago
- The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to o…☆379Updated last year
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆167Updated 2 years ago
- A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks☆363Updated last year
- Search Engines with Autoregressive Language models☆277Updated last year
- Train Dense Passage Retriever (DPR) with a single GPU☆128Updated 3 years ago
- For the code release of our arXiv paper "Revisiting Few-sample BERT Fine-tuning" (https://arxiv.org/abs/2006.05987).☆184Updated last year
- An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi☆253Updated last year
- [ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.o…☆605Updated 2 years ago
- Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data☆100Updated last year
- Materials for ACL-2022 tutorial: Knowledge-Augmented Methods for Natural Language Processing☆289Updated 2 years ago
- [NeurIPS'22 Spotlight] Data and code for our paper CoNT: Contrastive Neural Text Generation☆150Updated last year
- Implementation of Self-adjusting Dice Loss from "Dice Loss for Data-imbalanced NLP Tasks" paper☆105Updated 3 years ago
- Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)☆324Updated 10 months ago
- EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535☆141Updated 2 years ago
- [EMNLP 2021] Improving and Simplifying Pattern Exploiting Training☆153Updated 2 years ago
- Build Text Rerankers with Deep Language Models☆251Updated 8 months ago
- Fusion-in-Decoder☆550Updated last year
- ☆66Updated 3 years ago
- ☆116Updated 2 years ago