Video Experimental Relacionado
Updated: May 1, 2026
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
1.0K
ViSQA: Un conjunto de datos de referencia y modelos base para la respuesta a preguntas habladas en vietnamita
Le Trong Minh1,2, Nguyen Duc Thinh2, Nguyen Khanh Tho Loc1,2
1VNU University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam.
PloS one
|January 12, 2026
Resumen
Este estudio presenta ViSQA, un nuevo punto de referencia para la respuesta a preguntas habladas en vietnamita. Demuestra que los errores de reconocimiento automático del habla afectan significativamente el rendimiento, pero el entrenamiento con datos hablados mejora la robustez.
Área de la Ciencia:
- Procesamiento del Lenguaje Natural
- Reconocimiento del Habla
- Aprendizaje Automático
Sus antecedentes:
- La respuesta a preguntas habladas (SQA) integra el reconocimiento automático del habla (ASR) y la comprensión del lenguaje.
- Los puntos de referencia SQA existentes son limitados para idiomas de bajos recursos como el vietnamita.
- El SQA vietnamita carece de conjuntos de datos estandarizados para investigación y desarrollo.
Objetivo del estudio:
- Presentar ViSQA, el primer conjunto de datos de referencia para la respuesta a preguntas habladas en vietnamita.
- Permitir la evaluación sistemática de modelos SQA bajo una calidad variable de transcripción de reconocimiento automático del habla (ASR).
- Facilitar la investigación sobre el impacto de los errores de ASR en las tareas de comprensión del lenguaje posteriores.
Principales métodos:
- Se amplió el corpus UIT-ViQuAD utilizando un pipeline de texto a voz y ASR.
- Se crearon más de 13.000 pares de preguntas y respuestas con audio hablado alineado.
- Se incluyeron variantes de audio limpias y degradadas por ruido para una evaluación robusta.
- Se realizaron experimentos con cinco modelos basados en transformadores.
Principales resultados:
- Los errores de reconocimiento automático del habla (ASR) degradan sustancialmente el rendimiento del modelo SQA (por ejemplo, ViT5 EM: del 62,04% al 36,30%).
- Entrenar modelos con transcripciones habladas mejora la robustez contra los errores de ASR (por ejemplo, ViT5 EM: del 36,30% al 50,70%).
- Se demostró una caída significativa del rendimiento debido a imprecisiones en la transcripción.
Conclusiones:
- ViSQA sirve como un punto de referencia riguroso para los sistemas de respuesta a preguntas habladas en vietnamita.
- Destaca el impacto crítico de la calidad del ASR en el rendimiento del SQA.
- Proporciona una base para el desarrollo de modelos SQA más robustos para el vietnamita.
Videos de Conceptos Relacionados
01:07Data Collection by Survey
7.6K
The systematic method of obtaining and analyzing accurate information of a population is called data collection. A survey is a standard method of data collection that involves collecting information from a target human population about their experience, opinion, or knowledge of a product, service, or process. The responses are recorded and interpreted. The most common survey examples are written questionnaires, face-to-face or telephonic conversations, focus groups, and electronic (e-mail or...
7.6K
01:16Stratified Sampling Method
11.7K
Sampling is a technique to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. The sampling method ensures that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a stratified sample, divide the population into groups called strata and then take a...
To choose a stratified sample, divide the population into groups called strata and then take a...
11.7K
01:27Types of Surveys
468
Surveys are essential for marking property boundaries near water bodies. Different types of surveys are defined, each with its own function. Land surveys mark the property boundaries, while route surveys determine the position of properties on nearby highways. Topographic surveys create maps by capturing the three-dimensional features of the land. Hydrographic surveys focus on the shapes of underwater areas and the movement of streams through the properties. Mine surveys determine the relative...
468
01:30Typical Model Studies
842
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
842
01:22Language Development
1.1K
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
1.1K
01:17Cochran's Q Test
1.2K
Cochran's Q Test is a nonparametric statistical test used to determine if there are potential differences in the outcomes of three or more related groups on a binary (yes/no) or dichotomous outcome. It is essentially an extension of the McNemar Test, which is limited to two related samples - Cochran's Q test can handle three or more related samples, making it more versatile in scenarios where subjects are measured under multiple conditions. The test statistic follows a Chi-Square...
1.2K