RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation (CIKM'17)

Last update: Feb 10, 2022

Overview

RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation

This is the implementation of RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation.

Code

To run our code, please use the following commands:

g++ RATE.cpp -o RATE -std=c++11
./RATE [Training File] [Test File] [L, optional, default = 30] [T, optional, default = 1]

For example,

g++ RATE.cpp -o RATE -std=c++11
./RATE Dataset/train.txt Dataset/test.txt 40 1

The prediction results will be in ./result.txt (the first row is the classification result). Then you can run

python eval.py

to obtain evaluation metrics.

Dataset

We release the Europe dataset (Dataset/data.json), where each line is a json file with tweet text and metadata. Due to privacy issues, we have anonymized the whole dataset by representing each word/feature as an integer. An example is shown below.

{ 
   "label":0,
   "language":"3",
   "timezone":"5",
   "offset":"7",
   "userlang":"5",
   "latitude":"36.8901",
   "longitude":"30.6809",
   "text":"3332 2608 29"
}

Given the json file, one can run

cd Dataset/
python preprocess.py

to get training and testing data (Dataset/train.txt and Dataset/test.txt).

Result

Method	Micro-F1 (Acc)	Macro-F1	Mean Distance Error (km)	[email protected]
RATE	0.8905	0.5230	365.16	0.4315

Citation

@inproceedings{zhang2017rate,
  title={RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation},
  author={Zhang, Yu and Wei, Wei and Huang, Binxuan and Carley, Kathleen M and Zhang, Yan},
  booktitle={Proceedings of the 2017 ACM on Conference on Information and Knowledge Management},
  pages={2423--2426},
  year={2017},
  organization={ACM}
}

RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation (CIKM'17)

Related tags

Overview

RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation

Code

Dataset

Result

Citation

Owner

Yu Zhang

Code for You Only Cut Once: Boosting Data Augmentation with a Single Cut

Multimodal Co-Attention Transformer (MCAT) for Survival Prediction in Gigapixel Whole Slide Images

AWS provides a Python SDK, "Boto3" ,which can be used to access the AWS-account from the local.

A set of examples around hub for creating and processing datasets

[CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search

DumpSMBShare - A script to dump files and folders remotely from a Windows SMB share

Price-Prediction-For-a-Dream-Home - A machine learning based linear regression trained model for house price prediction.

Jarvis Project is a basic virtual assistant that uses TensorFlow for learning.

Locally Differentially Private Distributed Deep Learning via Knowledge Distillation (LDP-DL)

This is the code repository implementing the paper "TreePartNet: Neural Decomposition of Point Clouds for 3D Tree Reconstruction".

Public implementation of "Learning from Suboptimal Demonstration via Self-Supervised Reward Regression" from CoRL'21

[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining

A PyTorch Lightning solution to training OpenAI's CLIP from scratch.

A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

An Open Source Machine Learning Framework for Everyone

OpenMMLab Pose Estimation Toolbox and Benchmark.

Nested Graph Neural Network (NGNN) is a general framework to improve a base GNN's expressive power and performance

Short and long time series classification using convolutional neural networks

Fuse radar and camera for detection

Official Repository for our ICCV2021 paper: Continual Learning on Noisy Data Streams via Self-Purified Replay