Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis

Related tags

Deep LearningUIKA
Overview

Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis


Requirements

  • python 3.7
  • pytorch-gpu 1.7
  • numpy 1.19.4
  • pytorch_pretrained_bert 0.6.2
  • nltk 3.3
  • GloVe.840B.300d
  • bert-base-uncased

Environment

  • OS: Ubuntu-16.04.1
  • GPU: GeForce RTX 2080
  • CUDA: 10.2
  • cuDNN: v8.0.2

Dataset

  1. target datasets

    • raw data: "./dataset/"
    • processing data: "./dataset_npy/"
    • word embedding file: "./embeddings/"
  2. pretraining datasets

Training options

  • ds_name: the name of target dataset, ['14semeval_laptop', '14semeval_rest', 'Twitter'], default='14semeval_rest'
  • pre_name: the name of pretraining dataset, ['Amazon', 'Yelp'], default='Amazon'
  • bs: batch size to use during training, [64, 100, 200], default=64
  • learning_rate: learning rate to use, [0.001, 0.0005, 0.00001], default=0.001
  • n_epoch: number of epoch to use, [5, 10], default=10
  • model: the name of model, ['ABGCN', 'GCAE', 'ATAE'], default='ABGCN'
  • is_test: train or test the model, [0, 1], default=1
  • is_bert: GloVe-based or BERT-based, [0, 1], default=0
  • alpha: value of parameter \alpha in knowledge guidance loss of the paper, [0.5, 0.6, 0.7], default=0.06
  • stage: the number of training stage, [1, 2, 3, 4], default=4

Running

  1. running for the first stage (pretraining on the document)

    • python ./main.py -pre_name Amaozn -bs 256 -learning_rate 0.0005 -n_epoch 10 -model ABGCN -is_test 0 -is_bert 0 -stage 1
  2. running for the second stage

    • python ./main.py -ds_name 14semeval_laptop -bs 64 -learning_rate 0.001 -n_epoch 5 -model ABGCN -is_test 0 -is_bert 0 -alpha 0.6 -stage 2
  3. runing for the final stage

    • python ./main.py -ds_name 14semeval_laptop -bs 64 -learning_rate 0.001 -n_epoch 10 -model ABGCN -is_test 0 -is_bert 0 -stage 3
  4. training from scratch:

    • python ./main.py -ds_name 14semeval_laptop -bs 64 -learning_rate 0.001 -n_epoch 10 -model ABGCN -is_test 0 -is_bert 0 -stage 4

Evaluation

To have a quick look, we saved the best model weight trained on the target datasets in the "./best_model_weight". You can easily load them and test the performance. Due to the limited file space, we only provide the weight of ABGCN on 14semeval_laptop and 14semeval_rest datasets. You can evaluate the model weight with:

  • python ./main.py -ds_name 14semeval_laptop -bs 64 -model ABGCN -is_test 1 -is_bert 0
  • python ./main.py -ds_name 14semeval_rest-bs 64 -model ABGCN -is_test 1 -is_bert 0

Notes

  • The target datasets and more than 50% of the code are borrowed from TNet-ATT (Tang et.al, ACL2019).

  • The pretraining datasets are obtained from www.Kaggle.com.

torchsummaryDynamic: support real FLOPs calculation of dynamic network or user-custom PyTorch ops

torchsummaryDynamic Improved tool of torchsummaryX. torchsummaryDynamic support real FLOPs calculation of dynamic network or user-custom PyTorch ops.

Bohong Chen 1 Jan 07, 2022
Single Red Blood Cell Hydrodynamic Traps Via the Generative Design

Rbc-traps-generative-design - The generative design for single red clood cell hydrodynamic traps using GEFEST framework

Natural Systems Simulation Lab 4 Jun 16, 2022
Baselines for TrajNet++

TrajNet++ : The Trajectory Forecasting Framework PyTorch implementation of Human Trajectory Forecasting in Crowds: A Deep Learning Perspective TrajNet

VITA lab at EPFL 183 Jan 05, 2023
Implements pytorch code for the Accelerated SGD algorithm.

AccSGD This is the code associated with Accelerated SGD algorithm used in the paper On the insufficiency of existing momentum schemes for Stochastic O

205 Jan 02, 2023
As-ViT: Auto-scaling Vision Transformers without Training

As-ViT: Auto-scaling Vision Transformers without Training [PDF] Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou In ICLR 2

VITA 68 Sep 05, 2022
Template repository for managing machine learning research projects built with PyTorch-Lightning

Tutorial Repository with a minimal example for showing how to deploy training across various compute infrastructure.

Sidd Karamcheti 3 Feb 11, 2022
Autonomous Perception: 3D Object Detection with Complex-YOLO

Autonomous Perception: 3D Object Detection with Complex-YOLO LiDAR object detect

Thomas Dunlap 2 Feb 18, 2022
Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)

GraspNet Baseline Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020). [paper] [dataset] [API] [do

GraspNet 209 Dec 29, 2022
Survival analysis in Python

What is survival analysis and why should I learn it? Survival analysis was originally developed and applied heavily by the actuarial and medical commu

Cameron Davidson-Pilon 2k Jan 08, 2023
Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution

unfoldedVBA Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution This repository contains the Pytorch implementation of the unrolled

Yunshi HUANG 2 Jul 10, 2022
Collaborative forensic timeline analysis

Timesketch Table of Contents About Timesketch Getting started Community Contributing About Timesketch Timesketch is an open-source tool for collaborat

Google 2.1k Dec 28, 2022
PyTorch implementation of Wide Residual Networks with 1-bit weights by McDonnell (ICLR 2018)

1-bit Wide ResNet PyTorch implementation of training 1-bit Wide ResNets from this paper: Training wide residual networks for deployment using a single

Sergey Zagoruyko 122 Dec 07, 2022
This repository collects 100 papers related to negative sampling methods.

Negative-Sampling-Paper This repository collects 100 papers related to negative sampling methods, covering multiple research fields such as Recommenda

RUCAIBox 119 Dec 29, 2022
DCGAN-tensorflow - A tensorflow implementation of Deep Convolutional Generative Adversarial Networks

DCGAN in Tensorflow Tensorflow implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networ

Taehoon Kim 7.1k Dec 29, 2022
Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera.

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera. This project prepares training and t

305 Dec 16, 2022
[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

MiVOS (CVPR 2021) - Mask Propagation Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang [arXiv] [Paper PDF] [Project Page] [Papers with Code] This repo impleme

Rex Cheng 106 Jan 03, 2023
Hierarchical Uniform Manifold Approximation and Projection

HUMAP Hierarchical Manifold Approximation and Projection (HUMAP) is a technique based on UMAP for hierarchical non-linear dimensionality reduction. HU

Wilson Estécio Marcílio Júnior 160 Jan 06, 2023
GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process.

The GT4SD (Generative Toolkit for Scientific Discovery) is an open-source platform to accelerate hypothesis generation in the scientific discovery process. It provides a library for making state-of-t

Generative Toolkit 4 Scientific Discovery 142 Dec 24, 2022
Progressive Domain Adaptation for Object Detection

Progressive Domain Adaptation for Object Detection Implementation of our paper Progressive Domain Adaptation for Object Detection, based on pytorch-fa

96 Nov 25, 2022
Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information by Masato Tamura, Hiroki Ohashi, and Tomoaki Yosh

105 Dec 23, 2022