Jingtao Zhan's Projects
SIGIR'20: An Analysis of BERT in Document Ranking
BERT-related papers
An easy-to-use python toolkit for flexibly adapting various neural ranking models to any target domain.
The implementation of deep learning models for EEG classification.
SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.
CIKM 2022: Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
The Student's Guide to @lintool
Homepage
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Code for my PhD thesis. Library of quantization-based methods for fast similarity search in high dimensions. Presented at ECCV 18.
RepBERT is a competitive first-stage retrieval technique. It represents documents and queries with fixed-length contextualized embeddings. The inner products of them are regarded as relevance scores. Its efficiency is comparable to bag-of-words methods.
WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
Python library for reading ClueWeb09's warc files