Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Associative Learning01:27

Associative Learning

1.2K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.2K
Observational Learning01:12

Observational Learning

782
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
782
Purposive Learning01:22

Purposive Learning

411
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
411
Cognitive Learning01:21

Cognitive Learning

960
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
960
Stereotype Content Model02:16

Stereotype Content Model

15.3K
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...
15.3K
Per-Unit Sequence Models01:26

Per-Unit Sequence Models

400
An ideal Y-Y transformer, grounded through neutral impedances, displays per-unit sequence networks akin to those of a single-phase ideal transformer when subjected to balanced positive- or negative-sequence currents. These currents do not produce neutral currents, and their associated voltage drops.
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
400

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Unhealthy alcohol use detection in electronic health records: A comparative study using natural language processing.

Drug and alcohol dependence·2025
Same author

CODEIPPROMPT: Intellectual Property Infringement Assessment of Code Language Models.

Proceedings of machine learning research·2025
Same author

Equity in virtual care: A mixed methods study of perspectives from physicians.

Journal of telemedicine and telecare·2023
Same author

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics.

bioRxiv : the preprint server for biology·2022
Same author

Using social media to assess the consumer nutrition environment: comparing Yelp reviews with a direct observation audit instrument for grocery stores.

Public health nutrition·2018
Same author

How Hierarchical Topics Evolve in Large Text Corpora.

IEEE transactions on visualization and computer graphics·2015

Video Experimental Relacionado

Updated: Jan 8, 2026

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

983

HiCL: Aprendizaje Jerárquico Contrastivo de Incrustaciones de Oraciones No Supervisadas

Zhuofeng Wu1, Chaowei Xiao2, Vg Vinod Vydiswaran1

  • 1University of Michigan, Ann Arbor.

Findings of ACL. EMNLP. Conference on Empirical Methods in Natural Language Processing
|December 22, 2025
PubMed
Resumen

Este estudio presenta HiCL, un marco de aprendizaje jerárquico contrastivo que mejora la representación de texto al considerar las relaciones tanto locales como globales. HiCL mejora la eficiencia y efectividad del entrenamiento para tareas de similitud semántica de texto (STS).

Palabras clave:
aprendizaje jerárquicoaprendizaje contrastivorepresentación de textosimilitud semántica de textoprocesamiento del lenguaje naturalaprendizaje automático

Más Videos Relacionados

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

548

Videos de Experimentos Relacionados

Last Updated: Jan 8, 2026

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

983
Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

548

Área de la Ciencia:

  • Procesamiento del Lenguaje Natural
  • Aprendizaje Automático
  • Inteligencia Artificial

Sus antecedentes:

  • Los métodos tradicionales de codificación de secuencias a menudo pasan por alto las características de texto locales, lo que dificulta la generalización a textos más cortos.
  • Los enfoques existentes enfrentan desafíos para equilibrar la eficiencia del entrenamiento y la efectividad del aprendizaje de la representación.

Objetivo del estudio:

  • Proponer HiCL, un novedoso marco de aprendizaje jerárquico contrastivo.
  • Mejorar la eficiencia y efectividad del entrenamiento en el aprendizaje de la representación de texto.
  • Mejorar el rendimiento en tareas de similitud semántica de texto (STS).

Principales métodos:

  • HiCL emplea un enfoque jerárquico, procesando el texto tanto a nivel de segmento local como a nivel de secuencia global.
  • Utiliza el aprendizaje contrastivo tanto para las representaciones de segmentos como de secuencias.
  • La codificación eficiente se logra procesando primero segmentos cortos y luego agregándolos, abordando la complejidad cuadrática de los transformadores.

Principales resultados:

  • HiCL mejora significativamente el rendimiento del modelo SNCSE en siete tareas STS.
  • Se observó una mejora promedio de +0.2% en BERTlarge y +0.44% en RoBERTalarge.
  • El marco demuestra una efectividad y eficiencia superiores en comparación con los métodos tradicionales.

Conclusiones:

  • HiCL ofrece un enfoque efectivo y eficiente para el aprendizaje de la representación de texto.
  • La estrategia de aprendizaje jerárquico contrastivo modela con éxito tanto las relaciones de texto locales como globales.
  • Este marco proporciona una base sólida para avanzar en la investigación de la similitud semántica de texto.