Castorini (@castorini)
Guthub

castorini

Twitter logo Share LinkedIn logo Share Facebook logo Share

Top repositories

1

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Python
1,640
star
2

anserini

Anserini is a Lucene toolkit for reproducible information retrieval research
Java
1,025
star
3

daam

Diffusion attentive attribution maps for interpreting Stable Diffusion.
Jupyter Notebook
657
star
4

hedwig

PyTorch deep learning models for document classification
Python
591
star
5

honk

PyTorch implementations of neural network models for keyword spotting
Python
511
star
6

docTTTTTquery

docTTTTTquery document expansion model
Python
351
star
7

pygaggle

a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini
Jupyter Notebook
339
star
8

rank_llm

Repository for prompt-decoding using LLMs (GPT3.5, GPT4, Vicuna, and Zephyr)
Python
282
star
9

BuboQA

Simple question answering over knowledge graphs (Mohammed et al., NAACL 2018)
Python
281
star
10

howl

Wake word detection modeling toolkit for Firefox Voice, supporting open datasets like Speech Commands and Common Voice.
Python
198
star
11

castor

PyTorch deep learning models for text processing
Python
179
star
12

DeeBERT

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
Python
152
star
13

birch

Document ranking via sentence modeling using BERT
Python
143
star
14

covidex

A multi-stage neural search engine for the COVID-19 Open Research Dataset
TypeScript
137
star
15

duobert

Multi-stage passage ranking: monoBERT + duoBERT
Python
112
star
16

MP-CNN-Torch

Multi-Perspective Convolutional Neural Networks for modeling textual similarity (He et al., EMNLP 2015)
Lua
107
star
17

mr.tydi

Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.
Python
70
star
18

anserini-notebooks

Anserini notebooks
Jupyter Notebook
69
star
19

honkling

Web app for keyword spotting using TensorflowJS
JavaScript
69
star
20

afriberta

AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages
Python
66
star
21

dhr

Dense hybrid representations for text retrieval
Python
59
star
22

data

Castorini data
Python
59
star
23

NCE-CNN-Torch

Noise-Contrastive Estimation for Question Answering with Convolutional Neural Networks (Rao et al. CIKM 2016)
Lua
54
star
24

chatty-goose

A Python framework for conversational search
Python
40
star
25

transformers-arithmetic

Python
38
star
26

d-bert

Distilling BERT using natural language generation.
Python
35
star
27

hf-spacerini

Plug-and-play Search Interfaces with Pyserini and Hugging Face
Python
32
star
28

ragnarok

Retrieval-Augmented Generation battle!
Python
32
star
29

anserini-tools

Evaluation tools shared across anserini, pyserini, and pygaggle
Python
28
star
30

bertserini

BERTserini
Python
25
star
31

SimpleDBpediaQA

simple QA over knowledge graphs on DBpedia
Python
25
star
32

onboarding

Onboarding guide to Jimmy Lin's research group at the University of Waterloo
24
star
33

berxit

Python
21
star
34

umbrela

Python
20
star
35

VDPWI-NN-Torch

Very Deep Pairwise Word Interaction Neural Networks for modeling textual similarity (He and Lin, NAACL/HLT 2016)
Lua
19
star
36

perm-sc

Official codebase for permutation self-consistency.
Python
16
star
37

LiT5

Python
15
star
38

TREC-COVID

TREC-COVID results - this is a mirror of data on the TREC website in a more convenient format.
Roff
14
star
39

honk-models

Pre-trained models for Honk
11
star
40

howl-deploy

JavaScript deployment for Howl, the wake word detection modeling toolkit for Firefox Voice
JavaScript
10
star
41

Tweets2013-IA

The Tweets2013 Internet Archive collection
Scala
10
star
42

AfriTeVa-keji

Python
10
star
43

TrecQA-NegEx

Code and dataset for SIGIR 2017 short paper "Automatically Extracting High-Quality Negative Examples for Answer Selection in Question Answering"
Python
10
star
44

meanmax

MeanMax estimators.
Python
9
star
45

cqe

Python
9
star
46

SM-CNN-Torch

Torch implementation of Severyn and Moschitti's SIGIR 2015 CNN model for question answering
Lua
9
star
47

ONNX-demo

Python
8
star
48

anserini-notebooks-afirm2020

Colab notebooks for AFIRM '20
Jupyter Notebook
7
star
49

serverless-bert-reranking

Python
7
star
50

parrot

Keyword spotting using audio from speech synthesis services and YouTube
Python
7
star
51

touche-error-analysis

A reproduction study of the Touché 2020 dataset in the BEIR benchmark
Python
7
star
52

earlyexiting-monobert

Python
7
star
53

afriteva

Text - 2 - Text for African languages
Python
6
star
54

tct_colbert

Python
6
star
55

transformers-selective

Python
5
star
56

serverless-inference

Neural network inference on serverless architecture
Python
5
star
57

norbert

NorBERT: Anserini + dl4marco-bert
Python
4
star
58

anserini-spark

Anserini-Spark integration
Java
3
star
59

rank_llm_data

3
star
60

numbert

Passage Ranking Library using various pretrained LMs
Python
3
star
61

kim-cnn-vis

An in-browser visualization of Kim CNN
JavaScript
3
star
62

replicate-lce

Python
3
star
63

kws-gen-data

Data for KWS generator.
2
star
64

pyserini-data

Python
2
star
65

BuboQA-models

2
star
66

candle

PyTorch utilities for parameter pruning and multiplies reduction
Python
2
star
67

gooselight2

Search frontend for Anserini
Ruby
2
star
68

africlirmatrix

AfriCLIRMatrix is a test collection for cross-lingual information retrieval research in 15 diverse African languages.
2
star
69

biasprobe

Python
2
star
70

sigtestv

SIGnificance TESTing Violations: an end-to-end toolkit for evaluating neural networks.
Python
1
star
71

howl-models

1
star
72

SolrAnserini

Anserini integration with Solr
Python
1
star
73

gooselight

🦆 Anserini + Blacklight 🦆
Ruby
1
star
74

anlessini

Java
1
star
75

honkling-models

JavaScript
1
star
76

BuboQA-data

Hosting dataset for BuboQA
1
star
77

ragnarok_data

1
star