spacemanidol

Image2Smiles

Given an image of a molecule create a smiles or mol represenatation.

CS510IR

Everything revolving my work/experience in UIUC's CS510 Advanced Information Retrieval Spring 2021

512-Data-Mining-Project

Transfer Learning

anserini

Anserini is a Lucene toolkit for reproducible information retrieval research

augmentweb3

a

CAPOT

CLMS575S19

Seminar in Computational Linguistics focused on text representations taught by Dr. Yan Song

coretext

get your augmentation on.

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

DPR

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

Efficient-Web-Scale-Absractive-Summarization

Efficient Web Scale Abstractive summarization leveraging model asymmetry, scaling laws, and pseudo labeling

End2EndProductSearch

Website and Repo for TREC Product Search

gpt-neo

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

INCAS-Moral-Prediction

Predict moral values given a tweet

KALE

Easy and quick dual encoder compression via KLdiv embedding alignment

LMGroundedGlove

msmarco-1

website for MS Marco

PDFFIND

PDFFIND: PDF-Based Dataset for Information Retrieval and Natural Language Generation

RandomExpNotebooks

Ranking-Documents-From-Summaries

Learning to rank documents from Generative Summaries

RankingModelCompression

Compress Ranking Model Exps

robust-dense-retrieval

secpdf

spacemanidol.github.io

website

tevatron

Tevatron - A flexible toolkit for dense retrieval research and development.

TopologyInDPR

TREC-Product-Search

trec-product-search.github.io

UIUC-Thesis

zipfai