Code for our paper "Graph Pre-training for AMR Parsing and Generation" in ACL2022

Last update: Jan 03, 2023

Overview

AMRBART

An implementation for ACL2022 paper "Graph Pre-training for AMR Parsing and Generation". You may find our paper here (Arxiv).

Requirements

python 3.8
pytorch 1.8
transformers 4.8.2
pytorch-lightning 1.5.0
Tesla V100 or A100

We recommend to use conda to manage virtual environments:

conda env update --name <env> --file requirements.yml

We also provide a docker image here.

Data Processing

You may download the AMR corpora at LDC.

We follow Spring to preprocess AMR graphs:

# 1. install spring 
cd spring && pip install -e .
# 2. processing data
bash run-preprocess.sh

Pre-training

bash run-posttrain-bart-textinf-joint-denoising-6task-large-unified-V100.sh /path/to/BART/

Fine-tuning

For AMR Parsing, run

bash finetune_AMRbart_amrparsing.sh /path/to/pre-trained/AMRBART/ gpu_id

For AMR-to-text Generation, run

bash finetune_AMRbart_amr2text.sh /path/to/pre-trained/AMRBART/ gpu_id

Evaluation

For AMR Parsing, run

bash eval_AMRbart_amrparsing.sh /path/to/fine-tuned/AMRBART/ gpu_id

For AMR-to-text Generation, run

bash eval_AMRbart_amr2text.sh /path/to/fine-tuned/AMRBART/ gpu_id

Inference on your own data

If you want to run our code on your own data, try to transform your data into the format here, then run

For AMR Parsing, run

bash inference_amr.sh /path/to/fine-tuned/AMRBART/ gpu_id

For AMR-to-text Generation, run

bash inference_text.sh /path/to/fine-tuned/AMRBART/ gpu_id

Pre-trained Models

Pre-trained AMRBART

Setting	Params	checkpoint
AMRBART-base	142M	model
AMRBART-large	409M	model

Fine-tuned models on AMR-to-Text Generation

Setting	BLEU(tok)	BLEU(detok)	checkpoint	output
AMRBART-large (AMR2.0)	49.8	45.7	model	output
AMRBART-large (AMR3.0)	49.2	45.0	model	output

To get the tokenized bleu score, you need to use the scorer we provide here. We use this script in order to ensure comparability with previous approaches.

Fine-tuned models on AMR Parsing

Setting	Smatch	checkpoint	output
AMRBART-large (AMR2.0)	85.4	model	output
AMRBART-large (AMR3.0)	84.2	model	output

Todo

clean code

References

@inproceedings{bai-etal-2022-graph,
    title = "Graph Pre-training for {AMR} Parsing and Generation",
    author = "Bai, Xuefeng  and
      Chen, Yulong and
      Zhang, Yue",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "todo",
    doi = "todo",
    pages = "todo"
}

Code for our paper "Graph Pre-training for AMR Parsing and Generation" in ACL2022

Related tags

Overview

AMRBART

Requirements

Data Processing

Pre-training

Fine-tuning

Evaluation

Inference on your own data

Pre-trained Models

Pre-trained AMRBART

Fine-tuned models on AMR-to-Text Generation

Fine-tuned models on AMR Parsing

Todo

References

Owner

xfbai

PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

Plug-n-Play Reinforcement Learning in Python with OpenAI Gym and JAX

Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".

Stochastic gradient descent with model building

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch

Official Pytorch implementation for AAAI2021 paper (RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning)

PyTorch implementation of D2C: Diffuison-Decoding Models for Few-shot Conditional Generation.

Malware Analysis Neural Network project.

Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation.

Lacmus is a cross-platform application that helps to find people who are lost in the forest using computer vision and neural networks.

Code for LIGA-Stereo Detector, ICCV'21

Implementation for Paper "Inverting Generative Adversarial Renderer for Face Reconstruction"

Config files for my GitHub profile.

Adaptive Attention Span for Reinforcement Learning

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021

J.A.R.V.I.S is an AI virtual assistant made in python.

Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

An improvement of FasterGICP: Acceptance-rejection Sampling based 3D Lidar Odometry