worldbank / GISTEmbed
GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embeddings
☆42Updated last year
Alternatives and similar repositories for GISTEmbed:
Users that are interested in GISTEmbed are comparing it to the libraries listed below
- ☆54Updated 2 years ago
- Dense hybrid representations for text retrieval☆62Updated 2 years ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆75Updated 3 years ago
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval☆45Updated 6 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆48Updated last year
- ☆29Updated last year
- A multilingual version of MS MARCO passage ranking dataset☆144Updated last year
- Code, datasets, and checkpoints for the paper "Improving Passage Retrieval with Zero-Shot Question Generation (EMNLP 2022)"☆101Updated 2 years ago
- SIGIR 2021: Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling☆59Updated 3 years ago
- 🦮 Code and pretrained models for Findings of ACL 2022 paper "LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrie…☆49Updated 3 years ago
- CLIR version of ColBERT