Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
This work addresses the challenge of ensuring data quality in e-commerce product catalogs, which is crucial for retailers and platforms, but it is incremental as it builds on existing few-shot learning and meta-learning techniques.
The paper tackles the problem of validating textual attribute values in e-commerce catalogs, which are often noisy due to self-reporting by retailers, by proposing MetaBridge, a meta-learning latent variable approach that learns from limited labeled data and handles uncertainty in unseen categories. The result shows MetaBridge outperforms state-of-the-art methods in extensive experiments on real datasets from hundreds of categories.
Product catalogs are valuable resources for eCommerce website. In the catalog, a product is associated with multiple attributes whose values are short texts, such as product name, brand, functionality and flavor. Usually individual retailers self-report these key values, and thus the catalog information unavoidably contains noisy facts. Although existing deep neural network models have shown success in conducting cross-checking between two pieces of texts, their success has to be dependent upon a large set of quality labeled data, which are hard to obtain in this validation task: products span a variety of categories. To address the aforementioned challenges, we propose a novel meta-learning latent variable approach, called MetaBridge, which can learn transferable knowledge from a subset of categories with limited labeled data and capture the uncertainty of never-seen categories with unlabeled data. More specifically, we make the following contributions. (1) We formalize the problem of validating the textual attribute values of products from a variety of categories as a natural language inference task in the few-shot learning setting, and propose a meta-learning latent variable model to jointly process the signals obtained from product profiles and textual attribute values. (2) We propose to integrate meta learning and latent variable in a unified model to effectively capture the uncertainty of various categories. (3) We propose a novel objective function based on latent variable model in the few-shot learning setting, which ensures distribution consistency between unlabeled and labeled data and prevents overfitting by sampling from the learned distribution. Extensive experiments on real eCommerce datasets from hundreds of categories demonstrate the effectiveness of MetaBridge on textual attribute validation and its outstanding performance compared with state-of-the-art approaches.