Discriminative Universal Background Model Training for Speaker Recognition

Zhang, Weiqiang; Lu, Jia

doi:10.5772/16786

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LLM Evaluation Frameworks Current LLM evaluation frameworks primarily focus on measuring the competence of LLM-based agents in handling structured outputs . Existing evaluations predominantly rely on pre-formatted prompts to assess code completion [Wu et al, 2023, Zhang et al, 2024a, Yao et al, 2023. While recent advancements have seen autonomous agents specializing in intricate data science tasks, including analysis, visualization, and modeling [Qian et al, 2023, 2024, evaluations for these methods often depend on extensive human effort or use more powerful LLMs to assess the output [Dubois et al, 2023, Belyi et al, 2024.…”

Section: There Is a Uniform Distribution Of Goal Priorities In The Fi...mentioning

confidence: 99%

Data Augmentation for Intent Classification with Off-the-shelf Large Language Models

Sahu¹,

Rodríguez²,

Laradji³

et al. 2022

Proceedings of the 4th Workshop on NLP for Conversational AI

View full text Add to dashboard Cite

Data augmentation is a widely employed technique to alleviate the problem of data scarcity. In this work, we propose a prompting-based approach to generate labelled training data for intent classification with off-the-shelf language models (LMs) such as GPT-3. An advantage of this method is that no task-specific LM-fine-tuning for data generation is required; hence the method requires no hyper-parameter tuning and is applicable even when the available training data is very scarce. We evaluate the proposed method in a few-shot setting on four diverse intent classification tasks. We find that GPT-generated data significantly boosts the performance of intent classifiers when intents in consideration are sufficiently distinct from each other. In tasks with semantically close intents, we observe that the generated data is less helpful. Our analysis shows that this is because GPT often generates utterances that belong to a closely-related intent instead of the desired one. We present preliminary evidence that a prompting-based GPT classifier could be helpful in filtering the generated data to enhance its quality. 1

show abstract

Section: There Is a Uniform Distribution Of Goal Priorities In The Fi...mentioning

confidence: 99%