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
BLSTM-Convolutional Neural Networks for Respiratory Disease Diagnosis
Mohammad Hassan Khamechian - Mohammad Reza Akbarzadeh Tootoonchi
A New High gain Transformerless DC-DC Converter with Low Voltage Stress on Power Switches
Amirreza Bahadori - Ali Nadermohammadi - Mohammad Maalandish - Seyed Hossein Hosseini - Mehran Sabahi
The Use of Additive Decomposition and Deep Neural Network for Photovoltaic Power Forecasting
Fariba Dehghan - Mohsen Parsa Moghaddam - Maryam Imani
T-type L-2L De-Embedding Method for On-Wafer T-model Transmission Line Network
Milad Seyedi - Nasser Masoumi - Samad Sheikhaei
Impedance Evaluation of Plasmonic Nano Dipole Antennas Based on Guided TE Mode
Daniyal Khosh Maram - Hanieh Talati Aghdam - Hamed Abnavi
Forged Channel: A Breakthrough Approach for Accurate Parkinson's Disease Classification using Leave-One-Subject-Out Cross-Validation
SeyedAmirReza Hamidi - Kamal Mohamed-Pour - Mohammad Yousefi
A Combined Channel Approach for Decoding Intracranial EEG Signals: Enhancing Accuracy through Spatial Information Integration
Maryam Ostadsharif Memar - Navid Ziaei - Behzad Nazari
Data Association and Multi-Target Localization Using Particle Swarm Optimization
Seyed Mohammad B. Seyedin - Fereidoon Behnia
A Graphene Terahertz Detector based on the Photo-Thermoelectric Effect with Frequency Selectivity
Faramarz Alihosseini - Zahra Heshmatpanah - Hesam Zandi
A Dual-Band LPDA Antenna Based on MXene for High-Band 5G Application
Javad Shokri seyyedi - Reza Sarraf Shirazi - Gholamreza Moradi
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2