OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]

Abstract

Extraction of missing attribute values is to find values describing an attribute of interest from a free text input. Most past related work on extraction of missing attribute values work with a closed world assumption with the possible set of values known beforehand, or use dictionaries of values and hand-crafted features. How can we discover new attribute values that we have never seen before? Can we do this with limited human annotation or supervision? We study this problem in the context of product catalogs that often have missing values for many attributes of interest. In this work, we leverage product profile information such as titles and descriptions to discover missing values of product attributes. We develop a novel deep tagging model OpenTag for this extraction problem with the following contributions: (1) we formalize the problem as a sequence tagging task, and propose a joint model exploiting recurrent neural networks (specifically, bidirectional LSTM) to capture context and semantics, and Conditional Random Fields (CRF) to enforce tagging consistency, (2) we develop a novel attention mechanism to provide interpretable explanation for our model's decisions, (3) we propose a novel sampling strategy exploring active learning to reduce the burden of human annotation. OpenTag does not use any dictionary or hand-crafted features as in prior works. Extensive experiments in real-life datasets in different domains show that OpenTag with our active learning strategy discovers new attribute values from as few as 150 annotated samples (reduction in 3.3x amount of annotation effort) with a high F-score of 83%, outperforming state-of-the-art models.

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, UK, August 19-23, 2018

References in corpus (4)

• Natural Language Processing (almost) from Scratch
• End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
• Long Short-Term Memory-Networks for Machine Reading
• Attribute Extraction from Product Titles in eCommerce

Cited by in corpus (13)

• PAM: Understanding Product Images in Cross Product Category Attribute Extraction
• OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision
• B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions
• Using LLMs for the Extraction and Normalization of Product Attribute Values
• QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction
• Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction
• Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning
• AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding
• Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
• DESYR: Definition and Syntactic Representation Based Claim Detection on the Web
• Scoping Review of Active Learning Strategies and their Evaluation Environments for Entity Recognition Tasks
• LaTeX-Numeric: Language-agnostic Text attribute eXtraction for E-commerce Numeric Attributes
• An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling