The coda and data for "Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach" (ACL '21)

Overview

README

The coda and data for "Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach" (ACL '21)

Introduction

We propose a hierarchical core-fringe learning framework to measure fine-grained domain relevance of terms – the degree that a term is relevant to a broad (e.g., computer science) or narrow (e.g., deep learning) domain.

image-20210528201234901

Requirements

See requirements.txt

To install torch_geometric, please follow the instruction on pytorch_geometric

Reproduction

To reproduce the results in the paper (using word2vec embeddings)

Download data from Google Drive, unzip and put all the folders in the root directory of this repo (details about data are described below)

For broad domains (e.g., CS)

python run.py --domain cs --method cfl

For narrow domains (e.g., ML)

python run.py --domain cs --method hicfl --narrow

For narrow domains (PU setting) (e.g., ML)

python run.py --domain cs --method hicfl --narrow --pu

All experiments are run on an NVIDIA Quadro RTX 5000 with 16GB of memory under the PyTorch framework. The training of CFL for the CS domain can finish in 1 minute.

Query

To handle user query (using compositional GloVe embeddings as an example)

Download data from Google Drive, unzip and put all the folders in the root directory of this repo

Download GloVe embeddings from https://nlp.stanford.edu/projects/glove/, save the file to features/glove.6B.100d.txt

Example:

python query.py --domain cs --method cfl

The first run will train a model and save the model to model/. For the follow-up queries, the trained model can be loaded for prediction.

You can use the model either in a transductive or in an inductive setting (i.e., whether to include the query terms in training).

Options

You can check out the other options available using:

python run.py --help

Data

Data can be downloaded from Google Drive:

term-candidates/: list of seed terms. Format: term frequency

features/: features of terms (term embeddings trained by word2vec). To use compositional GloVe embeddings as features, you can download GloVe embeddings from https://nlp.stanford.edu/projects/glove/. To load the features, refer to utils.py for more details.

wikipedia/: Wikipedia search results for constructing the core-anchored semantic graph / automatic annotation

  • core-categories/: categories of core terms collected from Wikipedia. Format: term catogory ... category

  • gold-subcategories/: gold-subcategories for each domain collected from Wikipedia. Format: level#Category

  • ranking-results/: Wikipedia search results. 0 means using exact match, 1 means without exact match. Format: term result_1 ... result_k.

    The results are collected by the following script:

    # https://pypi.org/project/wikipedia/
    import wikipedia
    def get_wiki_search_result(term, mode=0):
        if mode==0:
            return wikipedia.search(f"\"{term}\"")
        else:
            return wikipedia.search(term)

train-valid-test/: train/valid/test split for evaluation with core terms

manual-data/:

  • ml2000-test.csv: manually created test set for ML
  • domain-relevance-comparison-pairs.csv: manually created test set for domain relevance comparison

Term lists

Several term lists with domain relevance scores produced by CFL/HiCFL are available on term-lists/

Format:

term  domain relevance score  core/fringe

Sample results for Machine Learning:

image-20210528201345177

Citation

The details of this repo are described in the following paper. If you find this repo useful, please kindly cite it:

@inproceedings{huang2021measuring,
  title={Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach},
  author={Huang, Jie and Chang, Kevin Chen-Chuan and Xiong, Jinjun and Hwu, Wen-mei},
  booktitle={Proceedings of ACL-IJCNLP},
  year={2021}
}
Owner
Jie Huang
Jie Huang
SweiNet is an uncertainty-quantifying shear wave speed (SWS) estimator for ultrasound shear wave elasticity (SWE) imaging.

SweiNet SweiNet is an uncertainty-quantifying shear wave speed (SWS) estimator for ultrasound shear wave elasticity (SWE) imaging. SweiNet takes as in

Felix Jin 3 Mar 31, 2022
Supervised Contrastive Learning for Downstream Optimized Sequence Representations

SupCL-Seq 📖 Supervised Contrastive Learning for Downstream Optimized Sequence representations (SupCS-Seq) accepted to be published in EMNLP 2021, ext

Hooman Sedghamiz 18 Oct 21, 2022
Acoustic mosquito detection code with Bayesian Neural Networks

HumBugDB Acoustic mosquito detection with Bayesian Neural Networks. Extract audio or features from our large-scale dataset on Zenodo. This repository

31 Nov 28, 2022
Hyper-parameter optimization for sklearn

hyperopt-sklearn Hyperopt-sklearn is Hyperopt-based model selection among machine learning algorithms in scikit-learn. See how to use hyperopt-sklearn

1.4k Jan 01, 2023
A Python library for differentiable optimal control on accelerators.

A Python library for differentiable optimal control on accelerators.

Google 80 Dec 21, 2022
Malware Env for OpenAI Gym

Malware Env for OpenAI Gym Citing If you use this code in a publication please cite the following paper: Hyrum S. Anderson, Anant Kharkar, Bobby Fila

ENDGAME 563 Dec 29, 2022
Official PyTorch implementation of "Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics".

Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics This repository is the official PyTorch implementation of "Physics-aware Differ

USC-Melady 46 Nov 20, 2022
Iterative Normalization: Beyond Standardization towards Efficient Whitening

IterNorm Code for reproducing the results in the following paper: Iterative Normalization: Beyond Standardization towards Efficient Whitening Lei Huan

Lei Huang 21 Dec 27, 2022
QT Py Media Knob using rotary encoder & neopixel ring

QTPy-Knob QT Py USB Media Knob using rotary encoder & neopixel ring The QTPy-Knob features: Media knob for volume up/down/mute with "qtpy-knob.py" Cir

Tod E. Kurt 56 Dec 30, 2022
The official GitHub repository for the Argoverse 2 dataset.

Argoverse 2 API Official GitHub repository for the Argoverse 2 family of datasets. If you have any questions or run into any problems with either the

Argo AI 156 Dec 23, 2022
This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

TransUNet This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation Usage

1.4k Jan 04, 2023
This repository contains the official code of the paper Equivariant Subgraph Aggregation Networks (ICLR 2022)

Equivariant Subgraph Aggregation Networks (ESAN) This repository contains the official code of the paper Equivariant Subgraph Aggregation Networks (IC

Beatrice Bevilacqua 59 Dec 13, 2022
A new codebase for Group Activity Recognition. It contains codes for ICCV 2021 paper: Spatio-Temporal Dynamic Inference Network for Group Activity Recognition and some other methods.

Spatio-Temporal Dynamic Inference Network for Group Activity Recognition The source codes for ICCV2021 Paper: Spatio-Temporal Dynamic Inference Networ

40 Dec 12, 2022
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks (SDPoint) This repository contains the cod

Jason Kuen 17 Jul 04, 2022
Pytorch code for "DPFM: Deep Partial Functional Maps" - 3DV 2021 (Oral)

DPFM Code for "DPFM: Deep Partial Functional Maps" - 3DV 2021 (Oral) Installation This implementation runs on python = 3.7, use pip to install depend

Souhaib Attaiki 29 Oct 03, 2022
Neural Surface Maps

Neural Surface Maps Official implementation of Neural Surface Maps - Luca Morreale, Noam Aigerman, Vladimir Kim, Niloy J. Mitra [Paper] [Project Page]

Luca Morreale 49 Dec 13, 2022
Sound Event Detection with FilterAugment

Sound Event Detection with FilterAugment Official implementation of Heavily Augmented Sound Event Detection utilizing Weak Predictions (DCASE2021 Chal

43 Aug 28, 2022
Super-Fast-Adversarial-Training - A PyTorch Implementation code for developing super fast adversarial training

Super-Fast-Adversarial-Training This is a PyTorch Implementation code for develo

LBK 26 Dec 02, 2022
Use deep learning, genetic programming and other methods to predict stock and market movements

StockPredictions Use classic tricks, neural networks, deep learning, genetic programming and other methods to predict stock and market movements. Both

Linda MacPhee-Cobb 386 Jan 03, 2023
CvT2DistilGPT2 is an encoder-to-decoder model that was developed for chest X-ray report generation.

CvT2DistilGPT2 Improving Chest X-Ray Report Generation by Leveraging Warm-Starting This repository houses the implementation of CvT2DistilGPT2 from [1

The Australian e-Health Research Centre 21 Dec 28, 2022