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

Transformers01:26

Transformers

1.5K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.5K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.3K
3.3K
Improving Translational Accuracy02:07

Improving Translational Accuracy

12.8K
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...
12.8K
Sum and Difference OpAmps01:22

Sum and Difference OpAmps

1.1K
Operational amplifiers (op-amps) are versatile devices that extend beyond amplification. In this context, two specific op-amp configurations are explored: the summing and difference amplifiers.
A summing amplifier, or an adder, utilizes an op-amp to merge multiple input signals into a single output signal. When audio signals are introduced into its input channels, the input resistors initiate currents that traverse feedback resistors, resulting in an output voltage. Applying Kirchhoff's current...
1.1K
Types Of Transformers01:16

Types Of Transformers

1.2K
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
1.2K
Energy Losses in Transformers01:21

Energy Losses in Transformers

1.1K
In an ideal transformer, it is assumed that there are no energy losses, and, hence, all the power at the primary winding is transferred to the secondary winding. However, in reality,  the transformers always have some energy losses, and, hence, the output power obtained at the secondary winding is less than the input power at the primary winding due to energy losses.
There are four main reasons for energy losses in transformers.
The first cause can be  the high resistance of the...
1.1K

You might also read

Related Articles

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

Sort by
Same author

Automated evaluation can distinguish the good and bad AI responses to patient questions about hospitalization.

NPJ digital medicine·2026
Same author

Quantifying Hallucinations in Language Language Models on Medical Textbooks.

ArXiv·2026
Same author

BioACE: An Automated Framework for Biomedical Answer and Citation Evaluations.

ArXiv·2026
Same author

A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes.

ArXiv·2026
Same author

A Dataset and Benchmark for Consumer Healthcare Question Summarization.

ArXiv·2026
Same author

A Dataset for Addressing Patient's Information Needs related to Clinical Course of Hospitalization.

Scientific data·2026
Same journal

A New Public Corpus for Clinical Section Identification: MedSecId.

Proceedings of COLING. International Conference on Computational Linguistics·2024
Same journal

Evaluating the Performance of Transformer-based Language Models for Neuroatypical Language.

Proceedings of COLING. International Conference on Computational Linguistics·2022
Same journal

Edinburgh_UCL_Health@SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination.

Proceedings of COLING. International Conference on Computational Linguistics·2022
Same journal

Summarizing Patients' Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models.

Proceedings of COLING. International Conference on Computational Linguistics·2022
Same journal

Autoregressive Affective Language Forecasting: A Self-Supervised Task.

Proceedings of COLING. International Conference on Computational Linguistics·2021
Same journal

Recognizing Medication related Entities in Hospital Discharge Summaries using Support Vector Machine.

Proceedings of COLING. International Conference on Computational Linguistics·2016
See all related articles

Related Experiment Video

Updated: Nov 26, 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

854

Flight of the PEGASUS? Comparing Transformers on Few-Shot and Zero-Shot Multi-document Abstractive Summarization.

Travis R Goodwin1, Max E Savery1, Dina Demner-Fushman1

  • 1U.S. National Library of Medicine, National Institutes of Health.

Proceedings of COLING. International Conference on Computational Linguistics
|December 9, 2020
PubMed
Summary
This summary is machine-generated.

State-of-the-art transformer models (BART, T5, PEGASUS) show similar performance in abstractive multi-document summarization with minimal training data. This suggests current benchmarks may not adequately differentiate advanced models for this task.

Related Experiment Videos

Last Updated: Nov 26, 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

854

Area of Science:

  • Natural Language Processing
  • Artificial Intelligence
  • Machine Learning

Background:

  • Pre-trained Transformer models achieve high performance in natural language processing tasks like summarization.
  • Existing research primarily focuses on single-document summarization with abundant data.
  • Highly-abstractive multi-document summarization, conditioned on user topics, remains less explored.

Purpose of the Study:

  • To investigate the performance of leading Transformer models (BART, T5, PEGASUS) in abstractive multi-document summarization.
  • To evaluate these models in zero-shot and few-shot learning settings on diverse datasets.
  • To assess the impact of limited labeled data on model performance for topic-conditioned summarization.

Main Methods:

  • Comparison of three state-of-the-art Transformer models: BART, T5, and PEGASUS.
  • Evaluation across four challenging summarization datasets (three general domain, one consumer health).
  • Assessment in both zero-shot and few-shot learning scenarios, with a focus on minimal labeled examples (as few as 10).

Main Results:

  • No statistically significant difference in summary quality was observed among BART, T5, and PEGASUS when provided with as few as 10 labeled examples.
  • Prior observed performance differences between these models diminish in few-shot, topic-conditioned multi-document summarization.
  • The models demonstrated comparable capabilities in generating abstractive summaries based on user-provided topics.

Conclusions:

  • Minimal labeled data (few-shot learning) can lead to comparable performance among top Transformer summarization models.
  • Current benchmark datasets may not be sufficiently challenging to differentiate advanced models in abstractive multi-document summarization.
  • Future research should focus on developing more abstractive and challenging benchmark collections to better evaluate state-of-the-art summarization systems.