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

Stereotype Content Model02:16

Stereotype Content Model

14.9K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.9K
Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.9K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.9K
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.9K
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...
11.9K
Machines: Problem Solving II01:30

Machines: Problem Solving II

374
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
374

You might also read

Related Articles

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

Sort by
Same author

Structural characteristics of the Phoebe hui chloroplast genome and phylogenetic analyses of Phoebe plants.

BMC genomics·2026
Same author

EEG Evidence for Dynamic Cross-Modal Adaptation Under Progressive Visual-Tactile Impairment.

Brain sciences·2026
Same author

Molecular factors controlling charge pair generation in organic photovoltaic materials.

Nature materials·2026
Same author

Integrative multi-omics reveal the regulatory mechanism of golden-thread wood color in Phoebe zhennan.

Plant physiology and biochemistry : PPB·2025
Same author

The PtrC2H2.2-6-PtrCYP86A7/A8 Module Regulates Poplar Drought Tolerance Through Mediating Cutin and Wax Biosynthesis Pathways.

Plant biotechnology journal·2025
Same author

Andromonoecious individuals of Populus schneideri respond more sensitively to N-deficiency and Cd pollution than males and females.

Tree physiology·2025

Related Experiment Video

Updated: Sep 16, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

692

A semi supervised framework for human and machine collaboration in computer assisted text refinement.

Yicheng Sun1, Yi Wang2, Hanbo Yang1

  • 1School of Mechanical and Precision Instrument Engineering, Xi'an University of Technology, Xi'an, China.

Scientific Reports
|July 7, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a semi-automatic method for creating text refinement datasets. It uses human judgment and auto-generation to produce more elegant sentences while reducing annotation workload.

Keywords:
Human–machine collaborationInfilling objectiveNatural language processParaphrase objectiveText refinement

More Related Videos

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
09:20

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

8.9K
Semi-automated Analysis of Mouse Skeletal Muscle Morphology and Fiber-type Composition
08:36

Semi-automated Analysis of Mouse Skeletal Muscle Morphology and Fiber-type Composition

Published on: August 31, 2017

10.7K

Related Experiment Videos

Last Updated: Sep 16, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

692
Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
09:20

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

8.9K
Semi-automated Analysis of Mouse Skeletal Muscle Morphology and Fiber-type Composition
08:36

Semi-automated Analysis of Mouse Skeletal Muscle Morphology and Fiber-type Composition

Published on: August 31, 2017

10.7K

Area of Science:

  • Natural Language Processing
  • Computational Linguistics

Background:

  • Automated text generation systems struggle with nuanced, elegant prose.
  • Annotation consistency is challenging in natural language generation tasks due to one-to-many input-output relationships.

Purpose of the Study:

  • To develop a semi-automatic method for constructing large-scale text refinement datasets.
  • To generate sentences with more elegant expressions while preserving original semantics.

Main Methods:

  • A semi-automatic approach combining auto-generation and human judgment.
  • Back translation to convert elegant sentences into ordinary expressions.
  • Iterative quality control involving data filtering and human judgment for screening.

Main Results:

  • Successfully created a large-scale text refinement dataset.
  • Significantly reduced annotation difficulty and workload compared to manual annotation.
  • Acquired substantial labeled data with minimal human effort.

Conclusions:

  • The proposed method effectively addresses annotation challenges in text refinement.
  • This approach provides a foundation for further research in generating elegant text.
  • Semi-automatic data construction is efficient for building specialized NLP datasets.