Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction
This addresses the challenge of quickly adapting to new products in e-commerce with minimal data, though it is incremental as it builds on existing prototypical networks.
The paper tackles the problem of extracting unseen attribute-value pairs for new products in e-commerce with limited labeled data by formulating it as a multi-label few-shot learning task, and their proposed Knowledge-Enhanced Attentive Framework outperforms state-of-the-art models on two datasets.
Existing attribute-value extraction (AVE) models require large quantities of labeled data for training. However, new products with new attribute-value pairs enter the market every day in real-world e-Commerce. Thus, we formulate AVE in multi-label few-shot learning (FSL), aiming to extract unseen attribute value pairs based on a small number of training examples. We propose a Knowledge-Enhanced Attentive Framework (KEAF) based on prototypical networks, leveraging the generated label description and category information to learn more discriminative prototypes. Besides, KEAF integrates with hybrid attention to reduce noise and capture more informative semantics for each class by calculating the label-relevant and query-related weights. To achieve multi-label inference, KEAF further learns a dynamic threshold by integrating the semantic information from both the support set and the query set. Extensive experiments with ablation studies conducted on two datasets demonstrate that KEAF outperforms other SOTA models for information extraction in FSL. The code can be found at: https://github.com/gjiaying/KEAF