Research Tools: code, datasets, & models

An SDK that provides the tools necessary to improve ranking by combining distance embeddings using integer linear programming (ILP; https://arxiv.org/abs/2005.10700 (opens in new tab)). This results in a more accurate optimized ranking of nodes relative…

State-of-the-art deep neural networks require large-scale labeled training data that is often either expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be…

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

This repository contains a Verified Boot implementation for the STM32H7 devices (specifically STM32H753ZI, STM32H743ZI) for the paper. The implementation contains DICE* code generated from the dice-star repository and implements the Hardware Abstraction Interface. The cmake…

This dataset consists of audio recordings of participants reading out stories in Rajasthani Hindi, one sentence at a time. We had 98 participants from Soda, Rajasthan. Each participant read 30 stories. In total, we have…

Dataset containing Aggregated and anonymized queries from across the world with Coronavirus intent. This dataset was curated from the Bing search logs (desktop users only) over the period of Jan 1st, 2020 – (Current Month…

This is the release record to open source a part of our recent research “SEED-Encoder”. It includes the model weights of the pretrained model, and the codes to add into our existing open-source repo ANCE…

CyberBattleSim is an experimentation research platform to investigate the interaction of automated agents operating in a simulated abstract enterprise network environment. The simulation provides a high-level abstraction of computer networks and cyber security concepts. Its…

Generates synthetic data and user interfaces for privacy-preserving data sharing and analysis. In many cases, the best way to share sensitive datasets is not to share the actual sensitive datasets, but user interfaces to derived…

Code-switching or code-mixing (CM) refers to the juxtaposition of linguistic units from two or more languages in a single conversation or sometimes even a single utterance. It is quite commonly observed in speech conversations of…