Boosting the AI research efficiency

Codes for papers on Large Language Models Personalization (LaMP)

MIMICS: A Large-Scale Data Collection for Search Clarification

search tool for toots on mastodon

The prime repository for state-of-the-art Multilingual Question Answering research and development.

A library for efficient similarity search and clustering of dense vectors.

A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

ClariQ: SCAI Workshop data challenge on conversational search clarification.

HiCAL is a system for efficient high-recall retrieval with an adaptable assessing interface.

Learning to Rank in TensorFlow

This is an implementation of the Dual Learning Algorithm with multi-layer feed-forward neural network for online unbiased learning to rank.

An benchmark dataset for personalized product search built on Amazon review data

Overview of venues, research themes and datasets relevant for conversational search.

Evaluation software used in the Text Retrieval Conference

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

categorical variational autoencoder using the Gumbel-Softmax estimator

CAsTUR is a dataset consisting of relevance labels for the TREC CAsT 2019 Utterance Relevance.

An Android app aimed for research on Unified Mobile Search, developed at Università della Svizzera italiana (USI), Lugano, Switzerland.

ISTAS: an in situ collection of cross-app mobile search queries

Free and Open Source, Distributed, RESTful Search Engine

Anserini is a Lucene toolkit for reproducible information retrieval research

An Extensible Conversational Information Seeking Platform

Qulac: A dataset on asking Questions for Lack of Clarity in open-domain information-seeking conversations.

Neural-IR-Explorer: A Content-Focused Tool to Explore Neural Re-Ranking Results

Reading Wikipedia to Answer Open-Domain Questions

Our paper dataset for some telegram news channels

A system for quickly generating training data with weak supervision

Qulac: A dataset on asking Questions for Lack of Clarity in open-domain information-seeking conversations.