Name: Nandan Thakur
Type: User
Company: University of Waterloo
Bio: Ph.D. Student working on NLP and IR at the University of Waterloo.
Twitter: nandan__thakur
Location: Waterloo, Ontario
Blog: thakur-nandan.github.io
Nandan Thakur's Projects
A Lucene toolkit for replicable information retrieval research
Awesome Topic Segmentation
Our Official Code Repositorty for QS-EIS-Challenge BatteryDEV 2022
Evaluation of BEIR Datasets using ColBERT retrieval model
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
BEIR Leaderboard
A reproduction of CITADEL and CITADEL+ checkpoints using dpr-scale repository
CC Information provided to easy run slurm scripts on CC Wiki
A Benchmark Data Set for Community Question-Answering Research
🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools
DeepCT and HDCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.
How to use the Keras Deep Learning library
Sample scripts used for uploading bulk datasets and models to HF
CS 679 Project Repository: Learning Efficient Autoencoders for Image Search
INCOME: An Easy Repository for Training and Evaluation of Index Compression Methods in Dense Retrieval. Includes BPR and JPQ.
Port of Google's language-detection library to Python.
Easy to use Multi-GPU Training of Retriever and Reranker
MTEB: Massive Text Embedding Benchmark
Microsoft OpenHack Challenge
Official repository for ORPO
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Personal Website | Nandan Thakur | Copyright © nandan-thakur.com, 2021
CS 886 Project on Adversarial Attacks on NLP models
Manipulate audio with a simple and easy high level interface
Question similarity with domain adaptation.
SDSC Summer Institute 2017 teaching material
Sentence Embeddings with BERT & XLNet
Societe Generale BrainWaves 2017-2018 Competition Solution Code