facebookresearch / SEALLinks
Search Engines with Autoregressive Language models
☆295Updated 2 years ago
Alternatives and similar repositories for SEAL
Users that are interested in SEAL are comparing it to the libraries listed below
Sorting:
- Scalable training for dense retrieval models.☆298Updated 7 months ago
- EMNLP 2021 - Pre-training architectures for dense retrieval☆254Updated 3 years ago
- a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini☆352Updated 2 years ago
- Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering☆174Updated 4 years ago
- Inquisitive Parrots for Search☆199Updated 7 months ago
- docTTTTTquery document expansion model☆373Updated 2 years ago
- Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"☆208Updated 4 years ago
- Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation☆114Updated 4 years ago
- Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch☆264Updated 2 years ago
- ☆224Updated 2 years ago
- Multi-hop dense retrieval for question answering☆216Updated 4 years ago
- Train Dense Passage Retriever (DPR) with a single GPU☆134Updated 4 years ago
- A multilingual version of MS MARCO passage ranking dataset☆146Updated 2 years ago
- EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535☆146Updated 3 years ago
- An original implementation of EMNLP 2020, "AmbigQA: Answering Ambiguous Open-domain Questions"☆120Updated 3 years ago
- Build Text Rerankers with Deep Language Models☆263Updated last year
- Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"☆62Updated 3 years ago
- MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, …☆130Updated 4 years ago
- Dense hybrid representations for text retrieval☆64Updated 2 years ago
- This is the code for our KILT leaderboard submissions (KGI + Re2G models).☆157Updated 3 months ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆79Updated 3 years ago
- Unified Learned Sparse Retrieval Framework☆68Updated last year
- Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper☆307Updated 8 months ago
- A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks☆380Updated last week
- Code, datasets, and checkpoints for the paper "Improving Passage Retrieval with Zero-Shot Question Generation (EMNLP 2022)"☆100Updated 3 years ago
- ☆328Updated 4 years ago
- ☆102Updated 3 years ago
- The autoregressive information extraction system GenIE (Generative Information Extraction) implemented in PyTorch.☆104Updated 2 years ago
- The original implementation of Min et al. "Nonparametric Masked Language Modeling" (paper https//arxiv.org/abs/2212.01349)☆158Updated 3 years ago
- A huggingface transformers implementation of "Transformer Memory as a Differentiable Search Index"☆175Updated 3 years ago