Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Improving Translational Accuracy02:07

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 Accuracy02:07

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...
Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Classification of Neurotransmitters01:30

Classification of Neurotransmitters

Neurotransmitters play a crucial role in the communication between neurons in the autonomic nervous system. Neurons in the autonomic nervous system can be cholinergic or adrenergic depending on the neurotransmitters synthesized. Cholinergic neurons use acetylcholine as their primary neurotransmitter. This includes all the preganglionic fibers of the sympathetic and pre- and postganglionic fibers of the parasympathetic nervous systems. In addition, neurons of the somatic nervous system also use...
Classification of Systems-II01:31

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
Aggregates Classification01:29

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

You might also read

Related Articles

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

Sort by
Same author

A deep learning and generative modeling pipeline for mining and engineering alkaline-stsable xylanases.

Bioresource technology·2026
Same author

DuA: Dual Attentive Transformer in Long-Term Continuous EEG Emotion Analysis.

IEEE journal of biomedical and health informatics·2026
Same author

Occupational Exposures in the Culinary Underbelly: Air Pollution in Restaurants.

Environmental science & technology·2026
Same author

High Efficiency Hole-Transport-Layer-Free Sb<sub>2</sub>S<sub>3</sub> Solar Cells via Platinum Back-Surface Doping.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

CT and MRI features of renal inflammatory myofibroblastic tumor and its differential diagnosis from clear cell renal cell carcinoma and chromophobe renal cell carcinoma: a study of 13 cases from two centers.

BMC urology·2026
Same author

Efficacy and safety of FLT3 inhibitors for acute myeloid leukemia: a network meta-analysis.

Frontiers in oncology·2026

Related Experiment Videos

An interpretable machine learning framework for classifying human and machine translations across genres.

Lingxi Fan1, Hongyang Du2, Gan Huang3

  • 1Hangzhou International Innovation Institute, Beihang University, Hangzhou, China.

Frontiers in Artificial Intelligence
|June 30, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces an interpretable machine learning framework to differentiate human and machine translations. It identifies key linguistic features like cohesion and morphological richness that distinguish human stylistic sensitivity from machine normalization.

Keywords:
SHapley Additive exPlanations (SHAP)machine and human translationmachine learningtext classificationtranslationese

Related Experiment Videos

Area of Science:

  • Computational Linguistics
  • Natural Language Processing
  • Machine Learning

Background:

  • Machine translation (MT) quality has significantly improved due to neural networks and large language models (LLMs).
  • The phenomenon of "translationese," or systematic linguistic features resulting from translation, has been studied qualitatively, but its quantitative characteristics remain unclear.
  • Distinguishing between human and machine-generated text is crucial for various applications.

Purpose of the Study:

  • To develop and validate an interpretable machine-learning framework for classifying Chinese-to-English human, Google-Translate, and ChatGPT outputs.
  • To quantitatively identify linguistic indicators that reliably differentiate human translations from machine translations across different genres.
  • To address the "black box" problem in text classification by providing explainable insights into the discrimination process.

Main Methods:

  • A dataset of 450 Chinese-to-English texts across news, novel, and technology genres was compiled.
  • An Elastic-Net logistic regression model selected 14 robust linguistic predictors from 308 candidates, normalized for text length.
  • A partial least squares discriminant analysis (PLS-DA) model was employed and validated using bootstrap resampling, achieving high performance metrics (F1-score=0.90, AUC=0.958).

Main Results:

  • The PLS-DA model successfully classified human, Google-Translate, and ChatGPT outputs with high accuracy.
  • SHapley Additive exPlanations (SHAP) identified normalized discourse-level cohesion (PIN), morphological richness (PRMD), and adposition density (d_adp) as the strongest genre-stable discriminators.
  • These features were found to act as proxies for informational density and stancetaking, reflecting human stylistic sensitivity versus machine normalization.

Conclusions:

  • The developed interpretable framework effectively distinguishes human from machine translations based on quantifiable linguistic features.
  • The findings align with established Corpus-Based Translation Studies theories on "shining-through" and "normalization."
  • This study offers a methodological template for explainable text classification, particularly for differentiating human and machine-generated content.