Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Stylistic analysis of translated languages: A perturbation-based XAI deep learning framework.

Dan Feng Huang¹, Dennis Tay²

¹School of Foreign Languages, Guangdong Polytechnic Normal University, Guangdong, China.

|July 7, 2026

Summary

This study introduces an explainable AI (XAI) deep learning (DL) framework to interpret text classification models. The XAI DL framework effectively distinguishes translated from non-translated texts by uncovering subtle stylistic differences.

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Offensive, hateful comment: A networked discourse practice of blame and petition for justice during COVID-19 on Chinese Weibo.

Discourse studies·2024

Same author

"We Need to Go Back Home (to) the Philippines Healthy": An Interpretive Phenomenological Analysis of Migrant Domestic Workers' Experiences of Having Breast Cancer in Hong Kong.

Qualitative health research·2024

Same author

Metaphorical language and psychopathological symptoms: a case study of trauma victims' metaphor use.

BMC psychology·2024

Same author

COVID-19 as WATER? The functions of WATER metaphors in the metaphorical representation of COVID-19.

PloS one·2023

Same author

Speech acts and the communicative functions of emojis in LIHKG online discussion forum amid COVID-19.

Frontiers in psychology·2023

Same author

Turning metaphor on its head: a "target-to-source transformation" approach in statistics education.

Frontiers in psychology·2023

Area of Science:

Natural Language Processing (NLP)
Artificial Intelligence (AI)
Machine Learning (ML)

Background:

Traditional machine learning and deep learning (DL) models are used for text classification in NLP.
DL models excel at representation learning but often function as black boxes, hindering interpretability.
Distinguishing translated from non-translated text reveals linguistic style differences.

Purpose of the Study:

To develop and demonstrate an explainable AI (XAI) deep learning (DL) framework for text classification.
To interpret the decisions of a DL model used to classify translated and non-translated texts.
To uncover stylistic differences between translated and non-translated texts beyond superficial features.

Main Methods:

A variational autoencoder (VAE) was trained using BERT embeddings from translated and non-translated texts.

Related Experiment Videos

A stacked ensemble of three classifiers was used to classify the VAE's latent representations.

A perturbation-based XAI method was implemented to interpret the DL model's classification decisions.

Main Results:

The VAE-based model achieved accuracy scores above 0.8 in distinguishing between translated and non-translated texts.
The XAI analysis successfully interpreted the DL model's decisions.
Stylistic differences between the text types were identified, extending beyond lexical and syntactic features.

Conclusions:

The developed XAI DL framework is effective for text classification and model interpretability.
This framework can uncover nuanced stylistic differences in text data.
The study demonstrates the potential of XAI DL for various NLP style analysis tasks.