TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing

Various robustness evaluation methodologies from different perspectives have been proposed for different natural language processing (NLP) tasks. These methods have often focused on either universal or task-specific generalization capabilities. In this work, we propose a multilingual robustness eval...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-05
Main Authors: Gui, Tao, Wang, Xiao, Zhang, Qi, Liu, Qin, Zou, Yicheng, Zhou, Xin, Zheng, Rui, Zhang, Chong, Wu, Qinzhuo, Ye, Jiacheng, Pang, Zexiong, Zhang, Yongxin, Li, Zhengyan, Ma, Ruotian, Zichu Fei, Cai, Ruijian, Zhao, Jun, Hu, Xingwu, Yan, Zhiheng, Tan, Yiding, Hu, Yuan, Bian, Qiyuan, Liu, Zhihua, Zhu, Bolin, Qin, Shan, Xing, Xiaoyu, Fu, Jinlan, Zhang, Yue, Peng, Minlong, Zheng, Xiaoqing, Zhou, Yaqian, Wei, Zhongyu, Qiu, Xipeng, Huang, Xuanjing
Format: Article
Language:English
Subjects:
Empirical analysis
Machine learning
Multilingualism
Natural language processing
Performance degradation
Robustness
State-of-the-art reviews
Transformations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Various robustness evaluation methodologies from different perspectives have been proposed for different natural language processing (NLP) tasks. These methods have often focused on either universal or task-specific generalization capabilities. In this work, we propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) that incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint enables practitioners to automatically evaluate their models from all aspects or to customize their evaluations as desired with just a few lines of code. To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one. TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness. To validate TextFlint's utility, we performed large-scale empirical evaluations (over 67,000 evaluations) on state-of-the-art deep learning models, classic supervised methods, and real-world systems. Almost all models showed significant performance degradation, including a decline of more than 50% of BERT's prediction accuracy on tasks such as aspect-level sentiment classification, named entity recognition, and natural language inference. Therefore, we call for the robustness to be included in the model evaluation, so as to promote the healthy development of NLP technology.
ISSN:2331-8422