Improving Short Text Classification With Augmented Data Using GPT-3
GPT-3 is a large-scale natural language model developed by OpenAI that can perform many different tasks, including topic classification. Although researchers claim that it requires only a small number of in-context examples to learn a task, in practice GPT-3 requires these training examples to be either of exceptional quality or a higher quantity than easily created by hand. To address this issue, this study teaches GPT-3 to classify whether a question is related to data science by augmenting a small training set with additional examples generated by GPT-3 itself. This study compares two classifiers: the GPT-3 Classification Endpoint with augmented examples, and the GPT-3 Completion Endpoint with an optimal training set chosen using a genetic algorithm. We find that while the augmented Completion Endpoint achieves upwards of 80 percent validation accuracy, using the augmented Classification Endpoint yields more consistent accuracy on unseen examples. In this way, giving large-scale machine learning models like GPT-3 the ability to propose their own additional training examples can result in improved classification performance.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationLanguage ModelingLanguage Modellingtext-classificationText ClassificationTopic ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Auditing LLMs for Algorithmic Fairness in Casenote-Augmented Tabular Prediction
LLMs are increasingly being considered for prediction tasks in high-stakes social service settings, but their algorithmic fairness properties in this context are poorly understood. In this short technical report, we audi…
Multi-class ClassificationOptimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by …
Sentiment AnalysisData AugmentationExploring Description-Augmented Dataless Intent Classification
In this work, we introduce several schemes to leverage description-augmented embedding similarity for dataless intent classification using current state-of-the-art (SOTA) text embedding models. We report results of our m…
AvgClassificationintent-classificationIntent ClassificationInterpretable Rationale Augmented Charge Prediction System
This paper proposes a neural based system to solve the essential interpretability problem existing in text classification, especially in charge prediction task. First, we use a deep reinforcement learning method to extra…
ClassificationDeep Reinforcement LearningGeneral ClassificationPrediction+5Keeping in Time: Adding Temporal Context to Sentiment Analysis Models
This paper presents a state-of-the-art solution to the LongEval CLEF 2023 Lab Task 2: LongEval-Classification. The goal of this task is to improve and preserve the performance of sentiment analysis models across shorter …
Language ModelingLanguage ModellingSentiment AnalysisTask 2