UKPLab / gplLinks
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
☆337Updated 2 years ago
Alternatives and similar repositories for gpl
Users that are interested in gpl are comparing it to the libraries listed below
Sorting:
- A multilingual version of MS MARCO passage ranking dataset☆145Updated last year
- Inquisitive Parrots for Search☆196Updated 3 months ago
- a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini☆351Updated last year
- docTTTTTquery document expansion model☆368Updated 2 years ago
- ☆86Updated 5 months ago
- Scalable training for dense retrieval models.☆299Updated 3 months ago
- Efficient Attention for Long Sequence Processing☆98Updated last year
- Search Engines with Autoregressive Language models☆291Updated 2 years ago
- A Python framework for performing information retrieval experiments, building on http://terrier.org/☆471Updated last week
- SpanMarker for Named Entity Recognition☆451Updated 8 months ago
- Set of vectorizers that extract keyphrases with part-of-speech patterns from a collection of text documents and convert them into a docum…☆265Updated 10 months ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆212Updated 4 months ago
- A library to synthesize text datasets using Large Language Models (LLM)☆152Updated 2 years ago
- Build Text Rerankers with Deep Language Models☆262Updated last year
- Neural information retrieval / Semantic search / Bi-encoders☆174Updated 2 years ago
- ☆366Updated last year
- This repository contains the code for "Generating Datasets with Pretrained Language Models".☆188Updated 4 years ago
- A large-scale multilingual dataset for Information Retrieval. Thorough human-annotations across 18 diverse languages.☆194Updated last year
- Provides a common interface to many IR ranking datasets.☆370Updated last week
- ☆40Updated 2 years ago
- Few-shot Named Entity Recognition☆123Updated 3 years ago
- Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch☆264Updated 2 years ago
- ☆169Updated last year
- Language model fine-tuning on NER with an easy interface and cross-domain evaluation. "T-NER: An All-Round Python Library for Transformer…☆391Updated 2 years ago
- Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13☆189Updated last week
- provides a common interface to many IR measure tools☆89Updated 2 weeks ago
- simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.☆398Updated 2 years ago
- Augmenty is an augmentation library based on spaCy for augmenting texts.☆156Updated last year
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆186Updated 2 months ago
- ☆184Updated 2 years ago