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
On the Design of Highly Efficient Harmonic Tuned Wideband Class F-1/F Power Amplifier
Mohammad Reza Zeinali - Amir Hossein Aalipour - Hossein Shamsi
Analysis and Simulation of the Formation and dimensions of Gate-Defined Double Quantum Dots
Mahya Mostafavi - Majid Shalchian
Design and simulation of an interleaved soft-switched CW-VM based boost converter for high power and high voltage applications
Soheil Hasani - Reza Beiranvand
Fixed-time consensus of unknown nonlinear multi-agent systems
Mohammad Hadi Rezaei - Ali Abooee
Anomaly Detection in Urban Water Distribution Grids Using Fog Computing Architecture
Sara Mirzaie - Mohammadreza Avazaghaei - Omid Bushehrian
بررسی توان و افزایش بازدهی در فرستنده سوئیچینگ لورن
عادل رضائیان - احمد عفیفی - جمشید ده پهلوانی
Machine Learning Approach for Retrieval of Complex Permittivity in Cavity Resonators
Kianoosh Kazemi - Gholamreza Moradi
A Combined Channel Approach for Decoding Intracranial EEG Signals: Enhancing Accuracy through Spatial Information Integration
Maryam Ostadsharif Memar - Navid Ziaei - Behzad Nazari
Bi-level Bidding Strategy of a Wind Power Producer Considering Local Intraday Demand Response Exchange Market
Ehsan Nokandi - Mostafa Vahedipour-Dahraie - Saeed Reza Goldani
بررسی و تحلیل تقابل تلفات و پروفیل ولتاژ به کمک الگوریتم ژنتیک چند هدفه در سیستم های قدرت در حضور سیستم های انتقال قدرت انعطاف پذیر
سجاد احمدنیا - حبیب رجبی مشهدی
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4