GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → xwhan → Extremely-Fine-Grained-Entity-Typing

xwhan / Extremely-Fine-Grained-Entity-Typing

Licence: MIT license
PyTorch implementation of our paper "Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing" (NAACL19)

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

naaclnatural-language-processingpytorchgraph-convolutional-networksentity-typing

Projects that are alternatives of or similar to Extremely-Fine-Grained-Entity-Typing

awesome-efficient-gnn
Code and resources on scalable and efficient Graph Neural Networks
Stars: ✭ 498 (+459.55%)
Mutual labels:  graph-convolutional-networks
chainer-graph-cnn
Chainer implementation of 'Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering' (https://arxiv.org/abs/1606.09375)
Stars: ✭ 67 (-24.72%)
Mutual labels:  graph-convolutional-networks
MoTIS
Mobile(iOS) Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP). Accepted at NAACL 2022.
Stars: ✭ 60 (-32.58%)
Mutual labels:  naacl
DCGCN
Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning (authors' MXNet implementation for the TACL19 paper)
Stars: ✭ 73 (-17.98%)
Mutual labels:  graph-convolutional-networks
GNN-Recommender-Systems
An index of recommendation algorithms that are based on Graph Neural Networks.
Stars: ✭ 505 (+467.42%)
Mutual labels:  graph-convolutional-networks
PaiConvMesh
Official repository for the paper "Learning Local Neighboring Structure for Robust 3D Shape Representation"
Stars: ✭ 19 (-78.65%)
Mutual labels:  graph-convolutional-networks
DSTGCN
codes of Deep Spatio-Temporal Graph Convolutional Network for Traffic Accident Prediction
Stars: ✭ 37 (-58.43%)
Mutual labels:  graph-convolutional-networks
Representation Learning on Graphs with Jumping Knowledge Networks
Representation Learning on Graphs with Jumping Knowledge Networks
Stars: ✭ 31 (-65.17%)
Mutual labels:  graph-convolutional-networks
CogIE
CogIE: An Information Extraction Toolkit for Bridging Text and CogNet. ACL 2021
Stars: ✭ 47 (-47.19%)
Mutual labels:  entity-typing
TextCategorization
⚡ Using deep learning (MLP, CNN, Graph CNN) to classify text in TensorFlow.
Stars: ✭ 30 (-66.29%)
Mutual labels:  graph-convolutional-networks
SimP-GCN
Implementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"
Stars: ✭ 43 (-51.69%)
Mutual labels:  graph-convolutional-networks
Few-NERD
Code and data of ACL 2021 paper "Few-NERD: A Few-shot Named Entity Recognition Dataset"
Stars: ✭ 317 (+256.18%)
Mutual labels:  entity-typing
graphml-tutorials
Tutorials for Machine Learning on Graphs
Stars: ✭ 125 (+40.45%)
Mutual labels:  graph-convolutional-networks
text gcn tutorial
A tutorial & minimal example (8min on CPU) for Graph Convolutional Networks for Text Classification. AAAI 2019
Stars: ✭ 23 (-74.16%)
Mutual labels:  graph-convolutional-networks
kglib
TypeDB-ML is the Machine Learning integrations library for TypeDB
Stars: ✭ 523 (+487.64%)
Mutual labels:  graph-convolutional-networks
SelfGNN
A PyTorch implementation of "SelfGNN: Self-supervised Graph Neural Networks without explicit negative sampling" paper, which appeared in The International Workshop on Self-Supervised Learning for the Web (SSL'21) @ the Web Conference 2021 (WWW'21).
Stars: ✭ 24 (-73.03%)
Mutual labels:  graph-convolutional-networks
Spatio-Temporal-papers
This project is a collection of recent research in areas such as new infrastructure and urban computing, including white papers, academic papers, AI lab and dataset etc.
Stars: ✭ 180 (+102.25%)
Mutual labels:  graph-convolutional-networks
pb-gcn
Code for the BMVC paper (http://bmvc2018.org/contents/papers/1003.pdf)
Stars: ✭ 32 (-64.04%)
Mutual labels:  graph-convolutional-networks
FreebaseQA
The release of the FreebaseQA data set (NAACL 2019).
Stars: ✭ 55 (-38.2%)
Mutual labels:  naacl
resolutions-2019
A list of data mining and machine learning papers that I implemented in 2019.
Stars: ✭ 19 (-78.65%)
Mutual labels:  graph-convolutional-networks
View All Similar Projects ➔

Code for our NAACL 2019 paper:

Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing

Paper link: http://arxiv.org/abs/1903.02591

Model Overview:

Requirements

  • PyTorch 0.4.1
  • tensorboardX
  • tqdm
  • gluonnlp

Running the code

First prepare the dataset and embeddings

1. Ultra-Fine experiments (10331 free-text labels and millions of training data)

Train the best model on Ultra-Fine
CUDA_VISIBLE_DEVICES=1 python main.py $RUN_ID$ -lstm_type single -model_debug -enhanced_mention -data_setup joint -add_crowd -multitask -gcn
You can then test your saved model
CUDA_VISIBLE_DEVICES=1 python main.py $RUN_ID$ -lstm_type single -model_debug -enhanced_mention -data_setup joint -add_crowd -multitask -gcn -load -mode test -eval_data crowd/test.json
Ablation experiments

a) w/o gcn

CUDA_VISIBLE_DEVICES=1 python main.py $RUN_ID$ -lstm_type single -model_debug -enhanced_mention -data_setup joint -add_crowd -multitask

b) w/o enhanced mention-context interaction

CUDA_VISIBLE_DEVICES=1 python main.py $RUN_ID$ -lstm_type single -gcn -enhanced_mention -data_setup joint -add_crowd -multitask

2. Experiments on OntoNotes

Training

CUDA_VISIBLE_DEVICES=1 python main.py $RUN_ID$ -lstm_type single -enhanced_mention -goal onto -gcn

Testing

CUDA_VISIBLE_DEVICES=1 python main.py $RUN_ID$ -lstm_type single -enhanced_mention -goal onto -gcn -mode test -load -eval_data ontonotes/g_dev.json

Notes

The meaning of the arguments can be found in config_parser.py

Acknowledgement

We thank Choi et al for the release of the Ultra-Fine dataset and the basic model: https://github.com/uwnlp/open_type.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].