Code for our EMNLP 2021 paper “Heterogeneous Graph Neural Networks for Keyphrase Generation”

Overview

GATER

This repository contains the code for our EMNLP 2021 paper “Heterogeneous Graph Neural Networks for Keyphrase Generation”.

Our implementation is built on the source code from keyphrase-generation-rl and fastNLP. Thanks for their work.

If you use this code, please cite our paper:

@inproceedings{ye2021heterogeneous,
  title={Heterogeneous Graph Neural Networks for Keyphrase Generation},
  author={Ye, Jiacheng and Cai, Ruijian and Gui, Tao and Zhang, Qi},
  booktitle={Proceedings of EMNLP},
  year={2021}
}

Dependency

  • python 3.5+
  • pytorch 1.0+
  • dgl 0.4.3
  • sentence_transformers 1.1.0
  • faiss 1.6.3

Dataset

The datasets can be downloaded from here, which are the tokenized version of the datasets provided by Ken Chen:

  • The testsets directory contains the five datasets for testing (i.e., inspec, krapivin, nus, and semeval and kp20k), where each of the datasets contains test_src.txt and test_trg.txt.
  • The kp20k_sorted directory contains the training and validation files (i.e., train_src.txt, train_trg.txt, valid_src.txt and valid_trg.txt).
  • Each line of the *_src.txt file is the source document, which contains the tokenized words of title <eos> abstract .
  • Each line of the *_trg.txt file contains the target keyphrases separated by an ; character. For example, each line can be like present keyphrase one;present keyphrase two;absent keyprhase one;absent keyphrase two.

Quick Start

The whole process includes the following steps:

  • Build tfidf: The retrievers/build_tfidf.py script is used to build the index for document retrieval.
  • Preprocessing: The preprocess.py script numericalizes the train_src.txt, train_trg.txt,valid_src.txt and valid_trg.txt files, and produces train.one2many.pt, valid.one2many.pt and vocab.pt.
  • Training: The train.py script loads the train.one2many.pt, valid.one2many.pt and vocab.pt file and performs training. We evaluate the model every 8000 batches on the valid set, and the model will be saved if the valid loss is lower than the previous one.
  • Decoding: The predict.py script loads the trained model and performs decoding on the five test datasets. The prediction file will be saved, which is like predicted keyphrase one;predicted keyphrase two;….
  • Evaluation: The evaluate_prediction.py script loads the ground-truth and predicted keyphrases, and calculates the [email protected]$ and [email protected]$ metrics.

For the sake of simplicity, we provide an one-click script in the script directory. You can run the following command to run the whole process with Gater model:

# under `One2One` paradigm
bash scripts/run_gater_one2one.sh

# under `One2Seq` paradigm
bash scripts/run_gater_one2seq.sh

You can also run the baseline model with the following command:

# under `One2One` paradigm
bash scripts/run_one2one.sh

# under `One2Seq` paradigm
bash scripts/run_one2seq.sh

Note:

  • Please download and unzip the datasets in the ./data directory first.
  • The Preprocessing procedure takes time because we have to pre-retrieve similiar references for each samples, and we also store them for the preparation of the training stage.
  • To run all the bash files smoothly, you may need to specify the correct home_dir (i.e., the absolute path to kg_gater dictionary) and the gpu id for CUDA_VISIBLE_DEVICES. We provide a small amount of data to quickly test whether your running environment is correct. You can test by running the following command:
bash scripts/run_small_gater_one2seq.sh
Event sourced bank - A wide-and-shallow example using the Python event sourcing library

Event Sourced Bank A "wide but shallow" example of using the Python event sourci

3 Mar 09, 2022
TRACER: Extreme Attention Guided Salient Object Tracing Network implementation in PyTorch

TRACER: Extreme Attention Guided Salient Object Tracing Network This paper was accepted at AAAI 2022 SA poster session. Datasets All datasets are avai

Karel 118 Dec 29, 2022
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

============================================================================================================ `MILA will stop developing Theano https:

9.6k Jan 06, 2023
Reproduces ResNet-V3 with pytorch

ResNeXt.pytorch Reproduces ResNet-V3 (Aggregated Residual Transformations for Deep Neural Networks) with pytorch. Tried on pytorch 1.6 Trains on Cifar

Pau Rodriguez 481 Dec 23, 2022
A PyTorch Implementation of Single Shot Scale-invariant Face Detector.

S³FD: Single Shot Scale-invariant Face Detector A PyTorch Implementation of Single Shot Scale-invariant Face Detector. Eval python wider_eval_pytorch.

carwin 235 Jan 07, 2023
[CVPR 21] Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.

Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting, CVPR 2021. Ayan Kumar Bhunia, Pinaki nath Chowdhury, Yongxin Yan

Ayan Kumar Bhunia 44 Dec 12, 2022
Unsupervised Video Interpolation using Cycle Consistency

Unsupervised Video Interpolation using Cycle Consistency Project | Paper | YouTube Unsupervised Video Interpolation using Cycle Consistency Fitsum A.

NVIDIA Corporation 100 Nov 30, 2022
Neural Oblivious Decision Ensembles

Neural Oblivious Decision Ensembles A supplementary code for anonymous ICLR 2020 submission. What does it do? It learns deep ensembles of oblivious di

25 Sep 21, 2022
Codes for AAAI 2022 paper: Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs

Context-Aware-Healthcare Codes for AAAI 2022 paper: Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs Download

LuChang 9 Dec 26, 2022
Code for paper Novel View Synthesis via Depth-guided Skip Connections

Novel View Synthesis via Depth-guided Skip Connections Code for paper Novel View Synthesis via Depth-guided Skip Connections @InProceedings{Hou_2021_W

8 Mar 14, 2022
DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion

DanceTrack DanceTrack is a benchmark for tracking multiple objects in uniform appearance and diverse motion. DanceTrack provides box and identity anno

260 Dec 28, 2022
Learning Continuous Image Representation with Local Implicit Image Function

LIIF This repository contains the official implementation for LIIF introduced in the following paper: Learning Continuous Image Representation with Lo

Yinbo Chen 1k Dec 25, 2022
Localized representation learning from Vision and Text (LoVT)

Localized Vision-Text Pre-Training Contrastive learning has proven effective for pre- training image models on unlabeled data and achieved great resul

Philip Müller 10 Dec 07, 2022
Codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing

Contrast and Mix (CoMix) The repository contains the codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Backgroun

Computer Vision and Intelligence Research (CVIR) 13 Dec 10, 2022
We will see a basic program that is basically a hint to brute force attack to crack passwords. In other words, we will make a program to Crack Any Password Using Python. Show some ❤️ by starring this repository!

Crack Any Password Using Python We will see a basic program that is basically a hint to brute force attack to crack passwords. In other words, we will

Ananya Chatterjee 11 Dec 03, 2022
This repository contain code on Novelty-Driven Binary Particle Swarm Optimisation for Truss Optimisation Problems.

This repository contain code on Novelty-Driven Binary Particle Swarm Optimisation for Truss Optimisation Problems. The main directory include the code

0 Dec 23, 2021
unet-family: Ultimate version

unet-family: Ultimate version 基于之前my-unet代码,我整理出来了这一份终极版本unet-family,方便其他人阅读。 相比于之前的my-unet代码,代码分类更加规范,有条理 对于clone下来的代码不需要修改各种复杂繁琐的路径问题,直接就可以运行。 并且代码有

2 Sep 19, 2022
PN-Net a neural field-based framework for depth estimation from single-view RGB images.

PN-Net We present a neural field-based framework for depth estimation from single-view RGB images. Rather than representing a 2D depth map as a single

1 Oct 02, 2021
An educational AI robot based on NVIDIA Jetson Nano.

JetBot Looking for a quick way to get started with JetBot? Many third party kits are now available! JetBot is an open-source robot based on NVIDIA Jet

NVIDIA AI IOT 2.6k Dec 29, 2022
Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"

Dangers of Bayesian Model Averaging under Covariate Shift This repository contains the code to reproduce the experiments in the paper Dangers of Bayes

Pavel Izmailov 25 Sep 21, 2022