A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

SPLADE: sparse neural search (SIGIR21, SIGIR22)

[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624

[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval

(ACL 2025 Main) A Comprehensive Benchmark for Code Information Retrieval.

Source code of paper 'LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval' (WWW 2023)

Official codebase for the ACL 2025 Findings paper: Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval.

Code repository of the NAACL'21 paper "CoRT: Complementary Rankings from Transformers"

Code for our project CROWN (Conversational Passage Ranking by Reasoning over Word Networks)

A machine for answering questions on federal crime sentences

Collaborated work with davidliyutong for course ICE6407P-260-M01 at SJTU

😷 Attempt on deep learning track challenge in TREC 2019 - https://microsoft.github.io/TREC-2019-Deep-Learning/

Qur'an QA 2023 Shared Task! Answering Questions on the Holy Qur'an @ ArabicNLP 2023, co-located with EMNLP 2023

The "Questions" project, part of Harvard's CS50 AI course, develops an AI system for answering questions by retrieving documents and passages from a text corpus using tf-idf. It aids in understanding natural language processing (NLP) and information retrieval techniques.

Augmented Dense-Sparse Retrieval for Longer Korean Passages

🖱️Generating spoilers for the clickbait posts