Georgetown Information Retrieval Lab

QuickUMLS

System for Medical Concept Extraction and Linking

cedr

Code for CEDR: Contextualized Embeddings for Document Ranking, accepted at SIGIR 2019.

OpenNIR

An end-to-end neural ad-hoc ranking pipeline.

ExtendedSumm

On Generating Extended Summaries of Long Documents

covid-neural-ir

semeval2018-task7

Code for "GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification"

emnlp17-depression

lrec2022-tbd3

prettr-neural-ir

simstring

SimString

ladr

CDS-search-dataset

CDS search dataset introduced in "Retrieving Medical Literature for
 Clinical Decision Support"

epic-neural-ir

multilingual-neural-ir

TSTRSum

gen2ir

HealthSurveillanceFramework

Framework for detecting health trends in social media posts

neuir-weak-supervision

Code for Content-Based Weak Supervision for Ad-Hoc Re-Ranking, accepted at SIGIR 2019.

query-clarification-data

ocr-correction

Experimental work to increase the accuracy of ocr by post-processing documents

RSDD-Time

curricula-neural-ir

Georgetown-IR-Lab.github.io

GitHub pages website

hbc-filter-northamerica

Twitter HBC client for storing Tweets located in North America

hbc-sample

Twitter HBC client for storing Tweets from the sample streaming API