Official repository for "PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation"

Related tags

Deep Learning pair-emnlp2020
Overview

pair-emnlp2020

Official repository for the paper:

Xinyu Hua and Lu Wang: PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation

If you find our work useful, please cite:

@inproceedings{hua-wang-2020-pair,
    title = "PAIR: Planning and Iterative Refinement in Pre-trained Transformersfor Long Text Generation",
    author = "Hua, Xinyu  and
      Wang, Lu",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
}

Requirements

  • Python 3.7
  • PyTorch 1.4.0
  • PyTorchLightning 0.9.0
  • transformers 3.3.0
  • numpy
  • tqdm
  • pycorenlp (for preprocessing nytimes data)
  • nltk (for preprocessing nytimes data)

Data

We release the data sets in the following link(1.2G uncompressed) Please download and uncompress the file, and put under ./data directory. For opinion and news domains, the The New York Times Annotated Corpus is licensed by LDC. We therefore only provide the ids for train/dev/test. Please follow the instructions to generate the dataset.

Text Planning

To train a BERT planner:

cd planning
python train.py \
    --data-path=../data/ \
    --domain=[arggen,opinion,news] \
    --exp-name=demo \
    --save-interval=1 \ # how frequent to save checkpoints 
    --max-epoch=30 \
    --lr=5e-4 \
    --warmup-updates=5000 \
    --train-set=train \
    --valid-set=dev \
    --tensorboard-logdir=tboard/ \
    --predict-keyphrase-offset \
    --max-samples=32 \ # max number of samples per batch
    [--quiet] \ # whether to print intermediate information

The checkpoints will be dumped to checkpoints/planning/[domain]/[exp-name]. Tensorboard will be available under planning/tboard/.

To run inference using a trained model, with greedy decoding:

cd planning
python decode.py \
    --data-path=../data/ \
    --domain=arggen \
    --test-set=test \
    --max-samples=32 \
    --predict-keyphrase-offset \
    --exp-name=demo \
    [--quiet]

The results will be saved to planning/output/.

Iterative Refinement

We provide implementations for four different setups:

  • Seq2seq: prompt -> tgt
  • KPSeq2seq: prompt + kp-set -> tgt
  • PAIR-light: prompt + kp-plan + masks -> tgt
  • PAIR-full: prompt + kp-plan + template -> tgt

To train a model:

cd refinement
python train.py \
    --domain=[arggen,opinion,news] \
    --setup=[seq2seq,kpseq2seq,pair-light,pair-full] \
    --train-set=train \
    --valid-set=dev \
    --train-batch-size=10 \
    --valid-batch-size=5 \
    --num-train-epochs=20 \
    --ckpt-dir=../checkpoints/[domain]/[setup]/demo \
    --tensorboard-dir=demo \
    [--quiet]

To run iterative refinement:

cd refinement
python generate.py \
    --domain=[arggen,opinion,news] \
    --setup=[seq2seq,kpseq2seq,pair-light,pair-full] \
    --test-set=test \
    --output-name=test_demo \
    --enforce-template-strategy=flexible \
    --do-sampling \
    --sampling-topk=100 \
    --sampling-topp=0.9 \
    --sample-times=3 \
    --ckpt-dir=../checkpoints/[domain]/[setup]/demo

Contact

Xinyu Hua (hua.x [at] northeastern.edu)

License

See the LICENSE file for details.

Comments
  • A question about evaluation

    A question about evaluation

    Thank you for such great work! And I have a question about the evaluation: some prompts have more than one reference arguments or news reports, and how do you evaluate them? Pair-wise or one-to-many?

    opened by StevenTang1998 4
  • Question about loglikehood_ratio.jsonl

    Question about loglikehood_ratio.jsonl

    Thanks for such an excellent work! I have a question about how to get the file loglikehood_ratio.jsonl, which prevents me from using the model in other datasets. If allowed, could you share related scripts? Thanks in advance!

    opened by wxl1999 2
  • Bugs about refinement

    Bugs about refinement

    After I run the planning code successfully, the refinement cannot work. I ran the refinement with pair-full under arggen dataset, the error is caused:

    Traceback (most recent call last):
  File "train.py", line 63, in <module>
    train()
  File "train.py", line 25, in train
    system = BARTSeq2seq.load_from_checkpoint(latest_ckpt_path)
  File "/home/tangtianyi/anaconda3/lib/python3.7/site-packages/pytorch_lightning/core/saving.py", line 135, in load_from_checkpoint
    checkpoint = pl_load(checkpoint_path, map_location=lambda storage, loc: storage)
  File "/home/tangtianyi/anaconda3/lib/python3.7/site-packages/pytorch_lightning/utilities/cloud_io.py", line 32, in load
    return torch.load(f, map_location=map_location)
  File "/home/tangtianyi/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 594, in load
    return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
  File "/home/tangtianyi/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 853, in _load
    result = unpickler.load()
ModuleNotFoundError: No module named 'modules'
    opened by StevenTang1998 2
  • Problems of evaluation

    Problems of evaluation

    Hi, we have run your code and generated the corresponding results (arggen_full) as well as utilized the evaluation toolkits implemented by Hugging Face https://huggingface.co/evaluate-metric. However, we cannot reproduce the results of ARGGEN of PAIR_{full} in Table 2. We provide the results below: B-4: 24.54 | R-L: 49.82 | MTR: 50.39 , which is not correspond to the results posted in your paper. We think this phenomenon may mainly be attributed to the different versions of the evaluation metrics. Could you provide your generation results for us to check or provide the URL of the evaluation metrics? Best regards!

    opened by Zecheng-Tang 0
  • FileNotFoundError

    FileNotFoundError

    Getting

    FileNotFoundError: [Errno 2] No such file or directory: '/data/model/xinyu/textgen-2020/pretrained_model/bert-base-cased-config.json'

    In File "planning/models/bert_models.py", line 59, in add_bert_config

    How can i get this file?

    opened by sandeep82945 0
Owner
Xinyu Hua
PhD student at Northeastern University
Xinyu Hua
GitHub
Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)

Certified Robustness to Adversarial Word Substitutions This is the official GitHub repository for the following paper: Certified Robustness to Adversa

Robin Jia 38 Oct 16, 2022
Official repository for the ICLR 2021 paper Evaluating the Disentanglement of Deep Generative Models with Manifold Topology

Official repository for the ICLR 2021 paper Evaluating the Disentanglement of Deep Generative Models with Manifold Topology Sharon Zhou, Eric Zelikman

Stanford Machine Learning Group 34 Nov 16, 2022
The repository offers the official implementation of our paper in PyTorch.

Cloth Interactive Transformer (CIT) Cloth Interactive Transformer for Virtual Try-On Bin Ren1, Hao Tang1, Fanyang Meng2, Runwei Ding3, Ling Shao4, Phi

Bingoren 49 Dec 1, 2022
Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.

Learning Associative Inference Using Fast Weight Memory This repository contains the offical code for the paper Learning Associative Inference Using F

Imanol Schlag 18 Oct 12, 2022
Official repository for "Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems"

Action-Based Conversations Dataset (ABCD) This respository contains the code and data for ABCD (Chen et al., 2021) Introduction Whereas existing goal-

ASAPP Research 49 Oct 9, 2022
Official repository for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21, Oral Presentation)

Official PyTorch Implementation for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'2021, Oral Presentation) HOTR: End-to-

Kakao Brain 114 Nov 28, 2022
Official repository for "Intriguing Properties of Vision Transformers" (2021)

Intriguing Properties of Vision Transformers Muzammal Naseer, Kanchana Ranasinghe, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, & Ming-Hsuan Yang P

Muzammal Naseer 155 Dec 27, 2022
Competitive Programming Club, Clinify's Official repository for CP problems hosting by club members.

Clinify-CPC_Programs This repository holds the record of the competitive programming club where the competitive coding aspirants are thriving hard and

Clinify Open Sauce 4 Aug 22, 2022
Official repository for "On Improving Adversarial Transferability of Vision Transformers" (2021)

Improving-Adversarial-Transferability-of-Vision-Transformers Muzammal Naseer, Kanchana Ranasinghe, Salman Khan, Fahad Khan, Fatih Porikli arxiv link A

Muzammal Naseer 47 Dec 2, 2022
This is the official repository of XVFI (eXtreme Video Frame Interpolation)

XVFI This is the official repository of XVFI (eXtreme Video Frame Interpolation), https://arxiv.org/abs/2103.16206 Last Update: 20210607 We provide th

Jihyong Oh 195 Dec 29, 2022
The official repository for BaMBNet

BaMBNet-Pytorch Paper

Junjun Jiang 18 Dec 4, 2022
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

selfcontact This repo is part of our project: On Self-Contact and Human Pose. [Project Page] [Paper] [MPI Project Page] It includes the main function

Lea Müller 68 Dec 6, 2022
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

SMPLify-XMC This repo is part of our project: On Self-Contact and Human Pose. [Project Page] [Paper] [MPI Project Page] License Software Copyright Lic

Lea Müller 83 Dec 14, 2022
This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.

NoW Evaluation This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard e

Soubhik Sanyal 71 Dec 30, 2022
Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers"

Recurrent Fast Weight Programmers This is the official repository containing the code we used to produce the experimental results reported in the pape

IDSIA 36 Nov 15, 2022
Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"

Easy-To-Hard The official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks". Gett

Avi Schwarzschild 52 Sep 8, 2022
Official repository for the CVPR 2021 paper "Learning Feature Aggregation for Deep 3D Morphable Models"

Deep3DMM Official repository for the CVPR 2021 paper Learning Feature Aggregation for Deep 3D Morphable Models. Requirements This code is tested on Py

null 38 Dec 27, 2022
Official repository for the paper, MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding.

MidiBERT-Piano Authors: Yi-Hui (Sophia) Chou, I-Chun (Bronwin) Chen Introduction This is the official repository for the paper, MidiBERT-Piano: Large-

null 137 Dec 15, 2022
Official repository of my book: "Deep Learning with PyTorch Step-by-Step: A Beginner's Guide"

This is the official repository of my book "Deep Learning with PyTorch Step-by-Step". Here you will find one Jupyter notebook for every chapter in the book.

Daniel Voigt Godoy 340 Jan 1, 2023