Cogito Ergo Sum's Projects
JPEG-MPO Decoder / Converter Library and CLI Tool
Haskell MQTT client.
MultiResolution Chemistry
Toolbox for the Multistep Regression Estimator
Python client for Mri server, supports easy plotting/updating
An AI for the board game "Mr. Jack"
All synthetic data used for the experiments described in MRKL white paper https://www.ai21.com/blog/jurassic-x-crossing-the-neuro-symbolic-chasm-with-the-mrkl-system.
Modular reinforcement learning
Implementation of mjml in rust
The MHC Restriction Ontology
Multilingual Reply Suggestion
Lightweight Ruby
mruby safe bindings for Rust
Fast abstraction for converting human-like times into milliseconds.
A Python Client Application that allows users to interact with the Microsoft Graph API.
Tools to compare metrics between datasets, accounting for population differences and invariant features.
Microsoft Security Code Analysis for GitHub Actions toolkit.
Command-line client for the Microsoft Genomics service
MessagePack implementation for Rust / msgpack.org[Rust]
A Julia implementation of MessagePack-RPC Server Library
Microsoft Graph client library for Python
website for MS Marco
Truly Conversational Search is the next logic step in the journey to generate intelligent and useful AI. To understand what this may mean, researchers have voiced a continuous desire to study how people currently converse with search engines. Traditionally, the desire to produce such a comprehensive dataset has been limited because those who have this data (Search Engines) have a responsibility to their users to maintain their privacy and cannot share the data publicly in a way that upholds the trusts users have in the Search Engines. Given these two powerful forces we believe we have a dataset and paradigm that meets both sets of needs: A artificial public dataset that approximates the true data and an ability to evaluate model performance on the real user behavior. What this means is we released a public dataset which is generated by creating artificial sessions using embedding similarity and will test on the original data. To say this again: we are not releasing any private user data but are releasing what we believe to be a good representation of true user interactions.
MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, and passage/document ranking
Submission archive for the MS MARCO document ranking leaderboard
MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension and question answering
Multi-String Pattern Matching Algorithm Using TrieHashNode
Microsoft JavaScript Cryptography Library
Type safe composable application configuration management in Python