UKPLab / gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577
☆322Updated last year
Related projects ⓘ
Alternatives and complementary repositories for gpl
- docTTTTTquery document expansion model☆355Updated last year
- Inquisitive Parrots for Search☆177Updated 8 months ago
- A multilingual version of MS MARCO passage ranking dataset☆141Updated last year
- a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini☆340Updated 10 months ago
- Search Engines with Autoregressive Language models☆277Updated last year
- ☆332Updated 11 months ago
- Build Text Rerankers with Deep Language Models☆251Updated 8 months ago
- Provides a common interface to many IR ranking datasets.☆319Updated this week
- Efficient Attention for Long Sequence Processing☆87Updated 10 months ago
- Tevatron - A flexible toolkit for neural retrieval research and development.☆517Updated 2 weeks ago
- Scalable training for dense retrieval models.☆270Updated last year
- ☆147Updated 4 months ago
- A large-scale multilingual dataset for Information Retrieval. Thorough human-annotations across 18 diverse languages.☆167Updated 3 months ago
- MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, …☆300Updated last year
- Set of vectorizers that extract keyphrases with part-of-speech patterns from a collection of text documents and convert them into a docum…☆253Updated this week
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆184Updated last month
- ☆179Updated last year
- Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch☆261Updated last year
- A Python framework for performing information retrieval experiments, building on http://terrier.org/☆415Updated this week
- EMNLP 2021 - Pre-training architectures for dense retrieval☆244Updated 2 years ago
- ☆83Updated 2 months ago
- This repository contains the code for "Generating Datasets with Pretrained Language Models".☆187Updated 3 years ago
- pytrec_eval is an Information Retrieval evaluation tool for Python, based on the popular trec_eval.☆290Updated last year
- Zero and Few shot named entity & relationships recognition☆348Updated last month
- A library to synthesize text datasets using Large Language Models (LLM)☆151Updated last year
- Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13☆157Updated this week
- This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with enti…☆242Updated last year
- Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper☆284Updated last year
- Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation☆108Updated 3 years ago
- Neural information retrieval / Semantic search / Bi-encoders☆167Updated last year