searchivarius

PyFastPFor

Python bindings for the fast integer compression library FastPFor.

AccurateLuceneBM25

Improving the effectiveness Lucene's BM25 (and testing it using Yahoo! Answers and Stack Overflow collections)

PermTest

Permutation algorithms to test statistical significance of experimental results.

BlogCode

Code used in Leonid Boytsov's blog: http://searchivarius.org

EphyraQuestionAnalysis

A collection of OpenEphyra components necessary for question analysis

inpars_light

Scripts to reproduce InPars light paper

long_doc_rank_model_analysis

pytorch-pretrained-BERT-mod

A slightly modified version of the older version of the transformer library pytorch-pretrained-BERT

clearnlp-clearnlp-2.0.2.mod

A patched clearnlp 2.0.2

OpenNMT-py

Open Source Neural Machine Translation in PyTorch

XMLIterator

SAX sux: an XMLIterator solution for XML documents with iterative structure.

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

ann-benchmarks

Benchmarks of approximate nearest neighbor libraries in Python

annographix

Structured information retrieval using SOLR (archival version)

anserini

A Lucene toolkit for replicable information retrieval research

DeepNLP-models-Pytorch

Pytorch implementations of various Deep NLP models in cs-224n(Stanford Univ)

fastscancount

Fast implementations of the scancount algorithm: C++ header-only library

medline-query-with-entities

pubmed-query-with-entities

metric-learn

Metric learning algorithms in Python

mgiza

A word alignment tool based on famous GIZA++, extended to support multi-threading, resume training and incremental training.

MSMARCO-Document-Ranking-Submissions

Submission archive for the MS MARCO document ranking leaderboard

MSMARCO-Passage-Ranking-Submissions

Submission archive for the MS MARCO passage ranking leaderboard

n2

TOROS N2 - lightweight approximate Nearest Neighbor library which runs faster even with large datasets

pystruct

Simple structured learning framework for python

searchivarius

sparse_text_util

A nearly SVMLight (but without the class label) Python writer

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

wikiextractor

A tool for extracting plain text from Wikipedia dumps

yodaqa_mavenized

YodaQuestionAnalysis