Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance

Overview

Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance

Abstract: Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution. Recently, several proposed debiasing methods are shown to be very effective in improving out-of-distribution performance. However, their improvements come at the expense of performance drop when models are evaluated on the in-distribution data, which contain examples with higher diversity. This seemingly inevitable trade-off may not tell us much about the changes in the reasoning and understanding capabilities of the resulting models on broader types of examples beyond the small subset represented in the out-of-distribution data. In this paper, we address this trade-off by introducing a novel debiasing method, called confidence regularization, which discourage models from exploiting biases while enabling them to receive enough incentive to learn from all the training examples. We evaluate our method on three NLU tasks and show that, in contrast to its predecessors, it improves the performance on out-of-distribution datasets (e.g., 7pp gain on HANS dataset) while maintaining the original in-distribution accuracy.

The repository contains the code to reproduce our work in debiasing NLU models without in-distribution degradation. We provide 2 runs of experiment that are shown in our paper:

  1. Debias MNLI model from syntactic bias and evaluate on HANS as the out-of-distribution data.
  2. Debias MNLI model from hypothesis-only bias and evaluate on MNLI-hard sets as the out-of-distribution data.

Requirements

The code requires python >= 3.6 and pytorch >= 1.1.0.

Additional required dependencies can be found in requirements.txt. Install all requirements by running:

pip install -r requirements.txt

Data

Our experiments use MNLI dataset version provided by GLUE benchmark. Download the file from here, and unzip under the directory ./dataset Additionally download the following files here for evaluating on hard/easy splits of both MNLI dev and test sets. The dataset directory should be structured as the following:

└── dataset 
    └── MNLI
        ├── train.tsv
        ├── dev_matched.tsv
        ├── dev_mismatched.tsv
        ├── dev_mismatched.tsv
        ├── dev_matched_easy.tsv
        ├── dev_matched_hard.tsv
        ├── dev_mismatched_easy.tsv
        ├── dev_mismatched_hard.tsv
        ├── multinli_hard
        │   ├── multinli_0.9_test_matched_unlabeled_hard.jsonl
        │   └── multinli_0.9_test_mismatched_unlabeled_hard.jsonl
        ├── multinli_test
        │   ├── multinli_0.9_test_matched_unlabeled.jsonl
        │   └── multinli_0.9_test_mismatched_unlabeled.jsonl
        └── original

Running the experiments

For each evaluation setting, use the --mode and --which_bias arguments to set the appropriate loss function and the type of bias to mitigate (e.g, hans, hypo).

To reproduce our result on MNLI ⮕ HANS, run the following:

cd src/
CUDA_VISIBLE_DEVICES=6 python train_distill_bert.py \
    --output_dir ../checkpoints/hans/bert_confreg_lr5_epoch3_seed444 \
    --do_train --do_eval --mode smoothed_distill \
    --seed 444 --which_bias hans

For the MNLI ⮕ hard splits, run the following:

cd src/
CUDA_VISIBLE_DEVICES=10 python train_distill_bert.py \
    --output_dir ../checkpoints/hypo/bert_confreg_lr5_epoch3_seed111 \
    --do_train --do_eval --mode smoothed_distill \
    --seed 111 --which_bias hypo

Expected results

Results on the MNLI ⮕ HANS setting:

Mode Seed MNLI-m MNLI-mm HANS avg.
None 111 84.57 84.72 62.04
conf-reg 111 84.17 85.02 69.62

Results on the MNLI ⮕ Hard-splits setting:

Mode Seed MNLI-m MNLI-mm MNLI-m hard MNLI-mm hard
None 111 84.62 84.71 76.07 76.75
conf-reg 111 85.01 84.87 78.02 78.89

Contact

Contact person: Ajie Utama, [email protected]

https://www.ukp.tu-darmstadt.de/

Please reach out to us for further questions or if you encounter any issue. You can cite this work by the following:

@InProceedings{UtamaDebias2020,
  author    = {Utama, P. Ajie and Moosavi, Nafise Sadat and Gurevych, Iryna},
  title     = {Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance},
  booktitle = {Proceedings of the 58th Conference of the Association for Computational Linguistics},
  month     = jul,
  year      = {2020},
  publisher = {Association for Computational Linguistics}
}

Acknowledgement

The code in this repository is build on the implementation of debiasing method by Clark et al. The original version can be found here

Owner
Ubiquitous Knowledge Processing Lab
Ubiquitous Knowledge Processing Lab
YOLOv5 detection interface - PyQt5 implementation

所有代码已上传,直接clone后,运行yolo_win.py即可开启界面。 2021/9/29:加入置信度选择 界面是在ultralytics的yolov5基础上建立的,界面使用pyqt5实现,内容较简单,娱乐而已。 功能: 模型选择 本地文件选择(视频图片均可) 开关摄像头

487 Dec 27, 2022
EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling

Frustratingly Simple Pretraining Alternatives to Masked Language Modeling This is the official implementation for "Frustratingly Simple Pretraining Al

Atsuki Yamaguchi 31 Nov 18, 2022
Learning Neural Painters Fast! using PyTorch and Fast.ai

The Joy of Neural Painting Learning Neural Painters Fast! using PyTorch and Fast.ai Blogpost with more details: The Joy of Neural Painting The impleme

Libre AI 72 Nov 10, 2022
Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods

ADGC: Awesome Deep Graph Clustering ADGC is a collection of state-of-the-art (SOTA), novel deep graph clustering methods (papers, codes and datasets).

yueliu1999 297 Dec 27, 2022
Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

Rotary Embeddings - Pytorch A standalone library for adding rotary embeddings to transformers in Pytorch, following its success as relative positional

Phil Wang 110 Dec 30, 2022
Transparent Transformer Segmentation

Transparent Transformer Segmentation Introduction This repository contains the data and code for IJCAI 2021 paper Segmenting transparent object in the

谢恩泽 140 Jan 02, 2023
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Introduction PyTorch3D provides efficient, reusable components for 3D Computer Vision research with PyTorch. Key features include: Data structure for

Facebook Research 6.8k Jan 01, 2023
A new data augmentation method for extreme lighting conditions.

Random Shadows and Highlights This repo has the source code for the paper: Random Shadows and Highlights: A new data augmentation method for extreme l

Osama Mazhar 35 Nov 26, 2022
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System Authors: Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai

Amazon Web Services - Labs 123 Dec 23, 2022
TICC is a python solver for efficiently segmenting and clustering a multivariate time series

TICC TICC is a python solver for efficiently segmenting and clustering a multivariate time series. It takes as input a T-by-n data matrix, a regulariz

406 Dec 12, 2022
Repo for flood prediction using LSTMs and HAND

Abstract Every year, floods cause billions of dollars’ worth of damages to life, crops, and property. With a proper early flood warning system in plac

1 Oct 27, 2021
Volumetric parameterization of the placenta to a flattened template

placenta-flattening A MATLAB algorithm for volumetric mesh parameterization. Developed for mapping a placenta segmentation derived from an MRI image t

Mazdak Abulnaga 12 Mar 14, 2022
Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021

PLOME:Pre-training with Misspelled Knowledge for Chinese Spelling Correction (ACL2021) This repository provides the code and data of the work in ACL20

197 Nov 26, 2022
Cross-Modal Contrastive Learning for Text-to-Image Generation

Cross-Modal Contrastive Learning for Text-to-Image Generation This repository hosts the open source JAX implementation of XMC-GAN. Setup instructions

Google Research 94 Nov 12, 2022
Official Pytorch implementation of Meta Internal Learning

Official Pytorch implementation of Meta Internal Learning

10 Aug 24, 2022
Catbird is an open source paraphrase generation toolkit based on PyTorch.

Catbird is an open source paraphrase generation toolkit based on PyTorch. Quick Start Requirements and Installation The project is based on PyTorch 1.

Afonso Salgado de Sousa 5 Dec 15, 2022
Multi-Modal Fingerprint Presentation Attack Detection: Evaluation On A New Dataset

PADISI USC Dataset This repository analyzes the PADISI-Finger dataset introduced in Multi-Modal Fingerprint Presentation Attack Detection: Evaluation

USC ISI VISTA Computer Vision 6 Feb 06, 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 08, 2022
Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集

English | 简体中文 Latest News 2021.10.25 Paper "Docking-based Virtual Screening with Multi-Task Learning" is accepted by BIBM 2021. 2021.07.29 PaddleHeli

633 Jan 04, 2023
Perception-aware multi-sensor fusion for 3D LiDAR semantic segmentation (ICCV 2021)

Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation (ICCV 2021) [中文|EN] 概述 本工作主要探索一种高效的多传感器(激光雷达和摄像头)融合点云语义分割方法。现有的多传感器融合方法主要将点云投影

ICE 126 Dec 30, 2022