thakur-nandan / incomeLinks
INCOME: An Easy Repository for Training and Evaluation of Index Compression Methods in Dense Retrieval. Includes BPR and JPQ.
☆24Updated last year
Alternatives and similar repositories for income
Users that are interested in income are comparing it to the libraries listed below
Sorting:
- SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.☆47Updated 2 years ago
- ☆46Updated 3 years ago
- Dense hybrid representations for text retrieval☆63Updated 2 years ago
- ☆38Updated 2 years ago
- One-stop shop for running and fine-tuning transformer-based language models for retrieval☆57Updated this week
- ☆37Updated 7 months ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆78Updated 3 years ago
- ☆54Updated 2 years ago
- ☆100Updated 2 years ago
- ☆86Updated 4 months ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆21Updated last month
- This repository contains the code for the paper 'PARM: Paragraph Aggregation Retrieval Model for Dense Document-to-Document Retrieval' pu…☆41Updated 3 years ago
- 🌏 Modular retrievers for zero-shot multilingual IR.☆28Updated last year
- 🦮 Code and pretrained models for Findings of ACL 2022 paper "LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrie…☆49Updated 3 years ago
- Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering☆172Updated 4 years ago
- ☆52Updated 3 weeks ago
- Official repository for our EACL 2023 paper "LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization" (https…☆44Updated last year
- Multilingual Entity Linking model by BELA model☆12Updated 2 years ago
- ☆11Updated 3 years ago
- Inquisitive Parrots for Search☆194Updated 2 months ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆29Updated 2 years ago
- Semantically Structured Sentence Embeddings☆66Updated 9 months ago
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval☆50Updated last month
- ☆29Updated last year
- Unified Learned Sparse Retrieval Framework☆66Updated last year
- Query-focused summarization data☆42Updated 2 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆49Updated last year
- Official Repository for "Hypencoder: Hypernetworks for Information Retrieval"☆27Updated 5 months ago
- ☆28Updated last year
- Cross language information retrieval pipeline☆18Updated 2 years ago