Establishing Strong Baselines for TripClick Health Retrieval; ECIR 2022

Overview

TripClick Baselines with Improved Training Data

Welcome 🙌 to the hub-repo of our paper:

Establishing Strong Baselines for TripClick Health Retrieval Sebastian Hofstätter, Sophia Althammer, Mete Sertkan and Allan Hanbury

https://arxiv.org/abs/2201.00365

tl;dr We create strong re-ranking and dense retrieval baselines (BERTCAT, BERTDOT, ColBERT, and TK) for TripClick (health ad-hoc retrieval). We improve the – originally too noisy – training data with a simple negative sampling policy. We achieve large gains over BM25 in the re-ranking and retrieval setting on TripClick, which were not achieved with the original baselines. We publish the improved training files for everyone to use.

If you have any questions, suggestions, or want to collaborate please don't hesitate to get in contact with us via Twitter or mail to [email protected]

Please cite our work as:

@misc{hofstaetter2022tripclick,
      title={Establishing Strong Baselines for TripClick Health Retrieval}, 
      author={Sebastian Hofst{\"a}tter and Sophia Althammer and Mete Sertkan and Allan Hanbury},
      year={2022},
      eprint={2201.00365},
      archivePrefix={arXiv},
      primaryClass={cs.IR}
}

Training Files

We publish the improved training files without the text content instead using the ids from TripClick (with permission from the TripClick owners); for the text content please get the full TripClick dataset from the TripClick Github page.

Our training files have the format query_id pos_passage_id neg_passage_id (with tab separation) and are available as a HuggingFace dataset: https://huggingface.co/datasets/sebastian-hofstaetter/tripclick-training

Source Code

The full source-code for our paper is here, as part of our matchmaker library: https://github.com/sebastian-hofstaetter/matchmaker

We provide getting started guides for training re-ranking and retrieval models, as well as a range of evaluation setups.

Pre-Trained Models

Unfortunately, the license of TripClick does not allow us to publish the trained models.

TripClick Baselines Results

For more information and commentary on the results, please see our ECIR paper.

BM25 Top200 Re-Ranking

Model BERT Instance HEAD TORSO TAIL
nDCG MRR nDCG MRR nDCG MRR
Original Baselines
BM25 -- .140 .276 .206 .283 .267 .258
ConvKNRM -- .198 .420 .243 .347 .271 .265
TK -- .208 .434 .272 .381 .295 .280
Our Improved Baselines
TK -- .232 .472 .300 .390 .345 .319
ColBERT SciBERT .270 .556 .326 .426 .374 .347
PubMedBERT-Abstract .278 .557 .340 .431 .387 .361
BERT_CAT DistilBERT .272 .556 .333 .427 .381 .355
BERT-Base .287 .579 .349 .453 .396 .366
SciBERT .294 .595 .360 .459 .408 .377
PubMedBERT-Full .298 .582 .365 .462 .412 .381
PubMedBERT-Abstract .296 .587 .359 .456 .409 .380
Ensemble (Last 3 BERT_CAT) .303 .601 .370 .472 .420 .392

Dense Retrieval Results

Model BERT Instance Head(DCTR)
[email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
Original Baselines
BM25 -- 31% .140 .276 .499 .621 .834
Our Improved Baselines
BERT_DOT DistilBERT 39% .236 .512 .550 .648 .813
SciBERT 41% .243 .530 .562 .640 .793
PubMedBERT 40% .235 .509 .582 .673 .828
Owner
Sebastian Hofstätter
PhD student; working on machine learning and information retrieval
Sebastian Hofstätter
Deep Image Matting implementation in PyTorch

Deep Image Matting Deep Image Matting paper implementation in PyTorch. Differences "fc6" is dropped. Indices pooling. "fc6" is clumpy, over 100 millio

Yang Liu 724 Dec 27, 2022
The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

Published by SpaceML • About SpaceML • Quick Colab Example Self-Supervised Learner The Self-Supervised Learner can be used to train a classifier with

SpaceML 92 Nov 30, 2022
Project to create an open-source 6 DoF input device

6DInputs A Project to create open-source 3D printed 6 DoF input devices Note the plural ('6DInputs' and 'devices') in the headings. We would like seve

RepRap Ltd 47 Jul 28, 2022
QTool: A Low-bit Quantization Toolbox for Deep Neural Networks in Computer Vision

This project provides abundant choices of quantization strategies (such as the quantization algorithms, training schedules and empirical tricks) for quantizing the deep neural networks into low-bit c

Monash Green AI Lab 51 Dec 10, 2022
Codes for "Template-free Prompt Tuning for Few-shot NER".

EntLM The source codes for EntLM. Dependencies: Cuda 10.1, python 3.6.5 To install the required packages by following commands: $ pip3 install -r requ

77 Dec 27, 2022
This is a simple plugin for Vim that allows you to use OpenAI Codex.

🤖 Vim Codex An AI plugin that does the work for you. This is a simple plugin for Vim that will allow you to use OpenAI Codex. To use this plugin you

Tom Dörr 195 Dec 28, 2022
Implementation of our paper 'RESA: Recurrent Feature-Shift Aggregator for Lane Detection' in AAAI2021.

RESA PyTorch implementation of the paper "RESA: Recurrent Feature-Shift Aggregator for Lane Detection". Our paper has been accepted by AAAI2021. Intro

137 Jan 02, 2023
Learning to Estimate Hidden Motions with Global Motion Aggregation

Learning to Estimate Hidden Motions with Global Motion Aggregation (GMA) This repository contains the source code for our paper: Learning to Estimate

Shihao Jiang (Zac) 221 Dec 18, 2022
Official PyTorch Implementation for "Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes"

PVDNet: Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes This repository contains the official PyTorch implementatio

Junyong Lee 98 Nov 06, 2022
Joint Versus Independent Multiview Hashing for Cross-View Retrieval[J] (IEEE TCYB 2021, PyTorch Code)

Thanks to the low storage cost and high query speed, cross-view hashing (CVH) has been successfully used for similarity search in multimedia retrieval. However, most existing CVH methods use all view

4 Nov 19, 2022
Compare outputs between layers written in Tensorflow and layers written in Pytorch

Compare outputs of Wasserstein GANs between TensorFlow vs Pytorch This is our testing module for the implementation of improved WGAN in Pytorch Prereq

Hung Nguyen 72 Dec 20, 2022
A module for solving and visualizing Schrödinger equation.

qmsolve This is an attempt at making a solid, easy to use solver, capable of solving and visualize the Schrödinger equation for multiple particles, an

506 Dec 28, 2022
Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions

Natural Posterior Network This repository provides the official implementation o

Oliver Borchert 54 Dec 06, 2022
Unofficial Tensorflow-Keras implementation of Fastformer based on paper [Fastformer: Additive Attention Can Be All You Need](https://arxiv.org/abs/2108.09084).

Fastformer-Keras Unofficial Tensorflow-Keras implementation of Fastformer based on paper Fastformer: Additive Attention Can Be All You Need. Tensorflo

Yam Peleg 10 Jan 30, 2022
Reinforcement Learning for the Blackjack

Reinforcement Learning for Blackjack Author: ZHA Mengyue Math Department of HKUST Problem Statement We study playing Blackjack by reinforcement learni

Dolores 3 Jan 24, 2022
A PyTorch implementation: "LASAFT-Net-v2: Listen, Attend and Separate by Attentively aggregating Frequency Transformation"

LASAFT-Net-v2 Listen, Attend and Separate by Attentively aggregating Frequency Transformation Woosung Choi, Yeong-Seok Jeong, Jinsung Kim, Jaehwa Chun

Woosung Choi 29 Jun 04, 2022
A Python implementation of the Locality Preserving Matching (LPM) method for pruning outliers in image matching.

LPM_Python A Python implementation of the Locality Preserving Matching (LPM) method for pruning outliers in image matching. The code is established ac

AoxiangFan 11 Nov 07, 2022
DeepLearning Anomalies Detection with Bluetooth Sensor Data

Final Year Project. Constructing models to create offline anomalies detection using Travel Time Data collected from Bluetooth sensors along the route.

1 Jan 10, 2022
A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX.

sam4onnx A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for

Katsuya Hyodo 6 May 15, 2022
FedML: A Research Library and Benchmark for Federated Machine Learning

FedML: A Research Library and Benchmark for Federated Machine Learning 📄 https://arxiv.org/abs/2007.13518 News 2021-02-01 (Award): #NeurIPS 2020# Fed

FedML-AI 2.3k Jan 08, 2023