RMIT CIDDA IR Group

SummaryRank

Python toolkit for ranking experiments on sentence/summary data

polyfuse

Fusion for TREC run files with popular fusion techniques

joint-cascade-ranking

Joint Optimization of Cascade Ranking Models (WSDM 19)

KrovetzStemmer

Python binding to the KrovetzStemmer package (C++ version)

LTR_Cascade

Code repo for the SIGIR '17 paper "Efficient Cost-Aware Cascade Ranking for Multi-Stage Retrieval"

AnswerPassageQuality

Code/data for SIGIR '18 paper "Ranking Documents by Answer-Passage Quality"

walert

Code and data for the Walert large language model-based chatbot

al-ef

Active Learning for Entity Filtering in Microblog Streams

bayesian-shallow

cikm20

Dataset and experiments from the CIKM 2020 Resource Track

FairTrec-2021-Runs

Corrected runs for TREC 2021 Fair Ranking Track (RMIT-IR)

pan2020-rmit

Repository for RMIT participation at the "Profiling Fake News Spreaders on Twitter" at PAN @ CLEF 2020

RBU

rmitb-trec-covid

conversationalIR

Overview of datasets and venues relevant for conversational search.

cred

CIDDA Research Day

crowdsourcing-algorithmic-bias

crowdsourcingTruthfulness

Repository with datasets used in the papers: "Crowdsourcing Truthfulness: The Impact of Judgment Scale and Assessor Bias" (ECIR'20) and "Can The Crowd Identify Misinformation Objectively? The Effects of Judgment Scale and Assessor's Background" (SIGIR'20)

factchecking-presentations

Data and code used in the CIKM’23 paper “Designing and Evaluating Presentation Strategies for Fact-Checked Content”

fair-arguments

Evaluating Fairness in Argument Retrieval

fairweb-1

CIDDA RMIT IR participation at the NTCIR FairWeb-1 task

fxt

A large scale feature extraction tool for text-based machine learning

IR-Physiological-Signals

User Study Materials

job-search-backstories

A collection of backstories for job search scenarios.

learning-similarity-functions-ORM

Data, code and results used for the SIGIR'14 "Learning Similarity Functions for Topic Detection in Online Reputation Monitoring" by Damiano Spina, Julio Gonzalo and Enrique Amigó

podcastsummaries

Dataset used to analyze user preferences of podcast summaries

rbc-combine

Rank-Biased Centroids

rmit-ir.github.io

Webpage repo for group.

Spoken-Conversational-Search

Dataset of spoken conversational search utterances

variable_impact_user_study