0% Complete
صفحه اصلی
/
سی و دومین کنفرانس بین المللی مهندسی برق
Integrating Model-Agnostic Meta-Learning with Advanced Language Embeddings for Few-Shot Intent Classification
نویسندگان :
Ali Rahimi
1
Hadi Veisi
2
1- دانشگاه تهران
2- دانشگاه تهران
کلمات کلیدی :
Few-shot learning،Model-Agnostic Meta-Learning (MAML)،Intent classification،Natural Language Processing (NLP)،BERT،LaBSE،Ada
چکیده :
Addressing the challenge of few-shot learning in intent classification tasks within Natural Language Processing (NLP), this study introduces a novel approach that harnesses the robust adaptation capabilities of Model-Agnostic Meta-Learning (MAML) combined with sophisticated language embeddings, namely BERT, LaBSE, and ada-002. The need for models to understand and classify intents with minimal training data is imperative to progress in creating versatile, responsive AI systems. We propose a methodology that leverages the generalizability of MAML and the deeply contextualized representations offered by state-of-the-art embeddings, allowing for significant improvements in Accuracy and data efficiency. We evaluate our approach using the CLINC150 dataset across a series of N-way \& K-shot configurations, demonstrating the efficacy of the proposed model with varying numbers of intent classes and examples. Our findings reveal that the ada-002 embeddings consistently provide superior performance in both 1-shot and 5-shot settings across all class configurations tested, indicating their potent synergy with meta-learning strategies. Specifically, openai-ada-002 achieved an accuracy of 97.07\% in the 5-Way \& 1-Shot setting and 99.1\% in the 5-Way \& 5-Shot setting. The outcomes of our experimental evaluation suggest that our approach also illuminates the potential of harmonious integration of cutting-edge language embeddings with meta-learning frameworks. This work provides a solid foundation for further exploration in optimizing few-shot intent classification, paving the way for creating AI systems proficient in understanding user intents with minimal exemplars. This research lays the groundwork for future advancements in few-shot intent classification, enabling the development of AI systems that require minimal training data to interpret user intent accurately.
لیست مقالات
لیست مقالات بایگانی شده
Intelligent Filter of $\mathcal{L}_{1}$ Adaptive Controller Using ANFIS System Optimized with Genetic Algorithm
Hossein Ahmadian - HeidarAli Talebi - Iman Sharifi
Ground-based Power Line Sag Measurement by Combining Data from a Smartphone and a Laser Rangefinder
Mohammad Javad Abdollahifard - Reza Bahrami
ساخت حسگر مقاومتی بخار اتانول مبتنی بر هتروساختار باریم تیتانات / اکسید روی آلاییده با نانوذرات نقره
محسن طاهری پور - نوید یثربی - شیرین نصراصفهانی - محمد حسین شیخی
امنیت سایبری در مواجه با تزریق اطلاعات نادرست به سیستم قدرت هوشمند و ارائه راهکار مقابله
مهدی جمشیدی آفارانی - مهرداد عابدی
Passive and Active Rectifier Combination for Hybrid Piezoelectric and Radio Frequency Energy Harvesting System
Mohammad reza Esaei - Mostafa Noohi - Ali Mirvakili
Design and Application of a Five-Level Cross-Switched Inverter in Low-Voltage Distribution System Voltage Compensation
Mohammad Farhadi-kangarlu - Yousef Neyshabouri - Asra Sotudeh
MAD-TI: Meta-path Aggregated-Graph Attention Network for Drug Target Interaction Prediction
Reza Shami Tanha - Maryam Sadighian - Arash Zabihian - Mohsen Hooshmand - Mohsen Afsharchi
Addressing Death from Heart Failure Using RACER Algorithm
Mohammad Mirsafaei - Alireza Basiri
Peer-to-peer Energy Sharing Considering Prosumers' Preferences and Load Uncertainties
Mohammad Bagher Moradi - Mohammad Hasan Nazari - Seyed Hossein Hosseinian - Hamed Nafisi
بررسی اثر فیدبک نوری بر مشخصه های دینامیکی لیزرهای قفل مد سیلیکونی
محمد شکرپور - محمد حسن یاوری
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3