code associated with ACL 2021 DExperts paper

Related tags

Deep LearningDExperts
Overview

DExperts

Hi! This repository contains code for the paper DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts to appear at ACL 2021. If you have any questions, please feel free to create a Github issue or reach out to the first author at [email protected].

Create a conda environment called dexperts with

conda env create -f environment.yml

Toxicity

To generate continuations with DExperts and score them for toxicity using the PerspectiveAPI toxicity scorer, run the following command.

OUTPUT_DIR=generations/toxicity/dexperts
PROMPTS_DATASET=prompts/nontoxic_prompts-10k.jsonl

python -m scripts.run_toxicity_experiment \
    --use-dataset \
    --dataset-file $PROMPTS_DATASET \
    --model-type dexperts \
    --model gpt2-large \
    --nontoxic-model $MODEL_DIR/finetuned_gpt2_nontoxic \
    --toxic-model $MODEL_DIR/finetuned_gpt2_toxic \
    --perspective-rate-limit $API_RATE \
    --alpha 2.0 \
    --filter_p 0.9 \
    $OUTPUT_DIR

In general, model_type is one of gpt2 (the base model), dexperts (our method), and pplm. With an OpenAI API key for GPT-3 access, you can also try gpt3 and dexperts-gpt3. Different methods have different additional parameters to specify; to see the commands we used for each method in our paper, please look under scripts/our_scripts/toxicity. For experiments with GeDi, we directly used the original authors' codebase.

When model_type is dexperts, we can steer away from toxicity using only a toxic anti-expert. To do this, leave --nontoxic-model empty, and DExperts will re-use the base model as the expert. The hyperparameter alpha controls the strength of steering over the base model. We use filter_p to use the nucleus from the base model, as described in Section 2.2 of our paper.

This script will create three files in OUTPUT_DIR: generations.jsonl with all of the generated continuations, perspective.jsonl with all the scores from Perspective API, and prompted_gens_[model_type].jsonl, which collates the previous two files.

To try a model's output on your own prompts, simply create your own prompts file! To see the format of the prompts file, see prompts/toy_prompt.jsonl.

Sentiment

To generate continuations with DExperts conditioned on sentiment prompts and score them for sentiment using HuggingFace's sentiment classifier, run the following command.

PROMPTS_DATASET=prompts/sentiment_prompts-10k/neutral_prompts.jsonl
OUTPUT_DIR=generations/sentiment/neutral_prompts/dexperts/positive/

python -m scripts.run_sentiment_experiment \
    --use-dataset \
    --dataset-file $PROMPTS_DATASET \
    --model-type dexperts \
    --model gpt2-large \
    --pos-model $MODEL_DIR/finetuned_gpt2_positive \
    --neg-model $MODEL_DIR/finetuned_gpt2_negative \
    --alpha 3.2 \
    --filter_p 0.9 \
    $OUTPUT_DIR

The model_type can be any of the options from before, with the addition of ctrl. Again, the full commands used for each method can be found under scripts/our_scripts/sentiment.

When model_type is dexperts, we always interpret --pos-model as the expert and --neg-model as the anti-expert; for negative steering, use alpha < 0. By leaving one of --pos-model or --neg-model empty, DExperts will re-use the base model as the missing expert or anti-expert.

Evaluation

To evaluate generated output for fluency and diversity, run the following command. The GENERATIONS_FILE should have the format prompted_gens_[model_type].jsonl.

python -m scripts.evaluation.evaluate_generations \
    --generations_file $GENERATIONS_FILE

Notebooks

Our jupyter notebooks are in notebooks/. To obtain the same tables and plots that appear in the paper, look in sentiment_results.ipynb, toxicity_results.ipynb, and human_eval_results.ipynb. To create your own prompts dataset with a couple lines of code, you can get started with prompts_playground.ipynb. Sample and compare generations from each model with review_sentiment_generations.ipynb and review_toxicity_generations.ipynb.

Downloading the original data and models from our paper

To download the prompts we used for evaluation, generations output by each model, and finetuning datasets from our paper, ensure you have gdown installed, then run the following commands inside the dexperts/ root directory. Descriptions of the contents of each of these folders can be found within the folder.

# prompts
gdown https://drive.google.com/uc?id=1bI49aJvmEoLdqSNb30JkORdsNJmv7Aep
unzip prompts.zip && rm prompts.zip
# generations
gdown https://drive.google.com/uc?id=10jL1-eCv8w3oeGFgA_jrel0enrNVdFW7
unzip generations.zip && rm generations.zip
# datasets
gdown https://drive.google.com/uc?id=1MeEjLPxQ77AYtzL0nd1hYJTlL8OJgHkI
unzip datasets.zip && rm datasets.zip

To download models from our paper,

mkdir models
cd models
# (anti-)expert models
gdown https://drive.google.com/uc?id=1HSrNMrq4OZ3nyTobNd2TZFcB5NYwluu-
unzip experts.zip && rm experts.zip
# DAPT models
gdown https://drive.google.com/uc?id=1eDlRU04s-H1elWWtPuDoBNAqyoqj3_p9
unzip dapt.zip && rm dapt.zip
# PPLM classifiers
gdown https://drive.google.com/uc?id=17s26QM9vJp9hCUkRBrDx5Wa__4BlrqGL
unzip pplm_classifiers.zip && rm pplm_classifiers.zip

Citation

@inproceedings{liu-etal-2021-dexperts,
    title = "{DExperts}: Decoding-Time Controlled Text Generation with Experts and Anti-Experts",
    author = "Alisa Liu and Maarten Sap and Ximing Lu and Swabha Swayamdipta and Chandra Bhagavatula and Noah A. Smith and Yejin Choi",
    booktitle = "Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP)",
    year = "2021",
    url = "https://arxiv.org/abs/2105.03023",
}

This code was built on top of allenai/real-toxicity-prompts and with inspiration from yangkevin2/naacl-2021-fudge-controlled-generation.

Owner
Alisa Liu
Alisa Liu
kapre: Keras Audio Preprocessors

Kapre Keras Audio Preprocessors - compute STFT, ISTFT, Melspectrogram, and others on GPU real-time. Tested on Python 3.6 and 3.7 Why Kapre? vs. Pre-co

Keunwoo Choi 867 Dec 29, 2022
Generates all variables from your .tf files into a variables.tf file.

tfvg Generates all variables from your .tf files into a variables.tf file. It searches for every var.variable_name in your .tf files and generates a v

1 Dec 01, 2022
A really easy-to-use and powerful sudoku solver.

SodukuSolver This is a really useful sudoku solver with a Qt gui. USAGE Enter the numbers in and click "RUN"! If you don't want to wait, simply press

Ujhhgtg Teams 11 Jun 02, 2022
A list of Machine Learning Art Colabs

ML Visual Art Colabs A list of cool Colabs on Machine Learning Imagemaking or other artistic purposes 3D Ken Burns Effect Ken Burns Effect by Manuel R

Derrick Schultz (he/him) 789 Dec 12, 2022
Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation

SUO-SLAM This repository hosts the code for our CVPR 2022 paper "Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation". ArXiv li

Robot Perception & Navigation Group (RPNG) 97 Jan 03, 2023
[CVPR 2022] TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing (CVPR 2022) This repository provides the official PyTorch impleme

Billy XU 128 Jan 03, 2023
Production First and Production Ready End-to-End Speech Recognition Toolkit

WeNet 中文版 Discussions | Docs | Papers | Runtime (x86) | Runtime (android) | Pretrained Models We share neural Net together. The main motivation of WeN

2.7k Jan 04, 2023
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral

News 05/10/2022 To make the comparison on ScanNet easier, we provide all quantitative and qualitative results of baselines here, including COLMAP, COL

ZJU3DV 365 Dec 30, 2022
A python program to hack instagram

hackinsta a program to hack instagram Yokoback_(instahack) is the file to open, you need libraries write on import. You run that file in the same fold

2 Jan 22, 2022
Spatio-Temporal Entropy Model (STEM) for end-to-end leaned video compression.

Spatio-Temporal Entropy Model A Pytorch Reproduction of Spatio-Temporal Entropy Model (STEM) for end-to-end leaned video compression. More details can

16 Nov 28, 2022
Pytorch reimplement of the paper "A Novel Cascade Binary Tagging Framework for Relational Triple Extraction" ACL2020. The original code is written in keras.

CasRel-pytorch-reimplement Pytorch reimplement of the paper "A Novel Cascade Binary Tagging Framework for Relational Triple Extraction" ACL2020. The o

longlongman 170 Dec 01, 2022
Artstation-Artistic-face-HQ Dataset (AAHQ)

Artstation-Artistic-face-HQ Dataset (AAHQ) Artstation-Artistic-face-HQ (AAHQ) is a high-quality image dataset of artistic-face images. It is proposed

onion 105 Dec 16, 2022
Automatic Number Plate Recognition using Contours and Convolution Neural Networks (CNN)

Cite our paper if you find this project useful https://www.ijariit.com/manuscripts/v7i4/V7I4-1139.pdf Abstract Image processing technology is used in

Adithya M 2 Jun 28, 2022
Chatbot in 200 lines of code using TensorLayer

Seq2Seq Chatbot This is a 200 lines implementation of Twitter/Cornell-Movie Chatbot, please read the following references before you read the code: Pr

TensorLayer Community 820 Dec 17, 2022
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

CIFS This repository provides codes for CIFS (ICML 2021). CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Sel

Hanshu YAN 19 Nov 12, 2022
Airborne Optical Sectioning (AOS) is a wide synthetic-aperture imaging technique

AOS: Airborne Optical Sectioning Airborne Optical Sectioning (AOS) is a wide synthetic-aperture imaging technique that employs manned or unmanned airc

JKU Linz, Institute of Computer Graphics 39 Dec 09, 2022
TrTr: Visual Tracking with Transformer

TrTr: Visual Tracking with Transformer We propose a novel tracker network based on a powerful attention mechanism called Transformer encoder-decoder a

趙 漠居(Zhao, Moju) 66 Dec 27, 2022
Gems & Holiday Package Prediction

Predictive_Modelling Gems & Holiday Package Prediction This project is based on 2 cases studies : Gems Price Prediction and Holiday Package prediction

Avnika Mehta 1 Jan 27, 2022
Voice control for Garry's Mod

WIP: Talonvoice GMod integrations Very work in progress voice control demo for Garry's Mod. HOWTO Install https://talonvoice.com/ Press https://i.imgu

Meta Construct 5 Nov 15, 2022
Code for ICLR2018 paper: Improving GAN Training via Binarized Representation Entropy (BRE) Regularization - Y. Cao · W Ding · Y.C. Lui · R. Huang

code for "Improving GAN Training via Binarized Representation Entropy (BRE) Regularization" (ICLR2018 paper) paper: https://arxiv.org/abs/1805.03644 G

21 Oct 12, 2020