castorini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Anserini is a Lucene toolkit for reproducible information retrieval research

Diffusion attentive attribution maps for interpreting Stable Diffusion.

RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.

PyTorch deep learning models for document classification

PyTorch implementations of neural network models for keyword spotting

docTTTTTquery document expansion model

a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini

Simple question answering over knowledge graphs (Mohammed et al., NAACL 2018)

Wake word detection modeling toolkit for Firefox Voice, supporting open datasets like Speech Commands and Common Voice.

PyTorch deep learning models for text processing

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Document ranking via sentence modeling using BERT

A multi-stage neural search engine for the COVID-19 Open Research Dataset

Multi-stage passage ranking: monoBERT + duoBERT

Multi-Perspective Convolutional Neural Networks for modeling textual similarity (He et al., EMNLP 2015)

AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages

Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.

Web app for keyword spotting using TensorflowJS

Anserini notebooks

Retrieval-Augmented Generation battle!

Dense hybrid representations for text retrieval

Castorini data

Noise-Contrastive Estimation for Question Answering with Convolutional Neural Networks (Rao et al. CIKM 2016)