AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding

Abstract

Automatic extraction of product attribute values is an important enabling technology in e-Commerce platforms. This task is usually modeled using sequence labeling architectures, with several extensions to handle multi-attribute extraction. One line of previous work constructs attribute-specific models, through separate decoders or entirely separate models. However, this approach constrains knowledge sharing across different attributes. Other contributions use a single multi-attribute model, with different techniques to embed attribute information. But sharing the entire network parameters across all attributes can limit the model's capacity to capture attribute-specific characteristics. In this paper we present AdaTag, which uses adaptive decoding to handle extraction. We parameterize the decoder with pretrained attribute embeddings, through a hypernetwork and a Mixture-of-Experts (MoE) module. This allows for separate, but semantically correlated, decoders to be generated on the fly for different attributes. This approach facilitates knowledge sharing, while maintaining the specificity of each attribute. Our experiments on a real-world e-Commerce dataset show marked improvements over previous methods.

arXiv commentAccepted to ACL-IJCNLP 2021

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Decoupled Weight Decay Regularization
• Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
• OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]
• Metadata Embeddings for User and Item Cold-start Recommendations
• Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product
• Adaptive Parameterization for Neural Dialogue Generation
• Learning Sparse Mixture of Experts for Visual Question Answering