TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing

03/21/2021
by   Tao Gui, et al.
20

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 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.

READ FULL TEXT

page 8

page 18

page 19

research
05/26/2020

ParsBERT: Transformer-based Model for Persian Language Understanding

The surge of pre-trained language models has begun a new era in the fiel...
research
01/13/2021

Robustness Gym: Unifying the NLP Evaluation Landscape

Despite impressive performance on standard benchmarks, deep neural netwo...
research
09/27/2021

Language Invariant Properties in Natural Language Processing

Meaning is context-dependent, but many properties of language (should) r...
research
11/15/2022

GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective

Pre-trained language models (PLMs) are known to improve the generalizati...
research
02/21/2023

ChatGPT: Jack of all trades, master of none

OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT...
research
02/03/2021

Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation

Public datasets are often used to evaluate the efficacy and generalizabi...
research
07/19/2023

Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation

Rising computational demands of modern natural language processing (NLP)...

Please sign up or login with your details

Forgot password? Click here to reset