Item categorization in the e-commerce domain

Shen, Dan; Ruvini, Jean David; Somaiya, Manas; Sundaresan, Neel

doi:10.1145/2063576.2063855

Cited by 21 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The nature of our problem is similar to those reported in (Bekkerman and Gavish, 2011;Shen et al, 2011;Shen et al, 2012b;Yu et al, 2013b;Sun et al, 2014;Kozareva, 2015;? ), but with more pronounced data quality issues.…”

Section: Related Worksupporting

confidence: 88%

See 1 more Smart Citation

Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce

Das

Xia

Levine³

et al. 2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

The cataloging of product listings through taxonomy categorization is a fundamental problem for any e-commerce marketplace, with applications ranging from personalized search recommendations to query understanding. However, manual and rule based approaches to categorization are not scalable. In this paper, we compare several classifiers for categorizing listings in both English and Japanese product catalogs. We show empirically that a combination of words from product titles, navigational breadcrumbs, and list prices, when available, improves results significantly. We outline a novel method using correspondence topic models and a lightweight manual process to reduce noise from mislabeled data in the training set. We contrast linear models, gradient boosted trees (GBTs) and convolutional neural networks (CNNs), and show that GBTs and CNNs yield the highest gains in error reduction. Finally, we show GBTs applied in a language-agnostic way on a largescale Japanese e-commerce dataset have improved taxonomy categorization performance over current state-of-the-art based on deep belief network models.

show abstract

Section: Related Worksupporting

confidence: 88%

“…) and splitting the taxonomy at predefined depths (Shen et al, 2011;? ) with smaller subtree models.…”

Section: Introductionmentioning

confidence: 99%

Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce

Das

Xia

Levine³

et al. 2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

show abstract

“…We select the top 10% features with the highest IG. The optimal number of features was cross-validated in a foregoing study under a similar setting [21,20]. There are 322,792 features in the coarse level.…”

Section: Coarse Level Classifiermentioning

confidence: 99%

Large-scale item categorization for e-commerce

Shen¹,

Ruvini

Sarwar

2012

Proceedings of the 21st ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

This paper studies the problem of leveraging computationally intensive classification algorithms for large scale text categorization problems. We propose a hierarchical approach which decomposes the classification problem into a coarse level task and a fine level task. A simple yet scalable classifier is applied to perform the coarse level classification while a more sophisticated model is used to separate classes at the fine level. However, instead of relying on a human-defined hierarchy to decompose the problem, we we use a graph algorithm to discover automatically groups of highly similar classes. As an illustrative example, we apply our approach to real-world industrial data from eBay, a major e-commerce site where the goal is to classify live items into a large taxonomy of categories. In such industrial setting, classification is very challenging due to the number of classes, the amount of training data, the size of the feature space and the realworld requirements on the response time. We demonstrate through extensive experimental evaluation that (1) the proposed hierarchical approach is superior to flat models, and (2) the data-driven extraction of latent groups works significantly better than the existing human-defined hierarchy.

show abstract

“…Product classi cation has been studied in [5,6,13,19,30,31], mostly in a multi-level (or hierarchical) se ing. However, given the dynamic taxonomy in nature, product classi cation has not been studied as an open-world learning problem.…”

Section: Related Workmentioning

confidence: 99%

Open-world Learning and Application to Product Classification

Liu

Shu

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

Classic supervised learning makes the closed-world assumption that the classes seen in testing must have appeared in training. However, this assumption is o en violated in real-world applications. For example, in a social media site, new topics emerge constantly and in e-commerce, new categories of products appear daily. A model that cannot detect new/unseen topics or products is hard to function well in such open environments. A desirable model working in such environments must be able to (1) reject examples from unseen classes (not appeared in training) and (2) incrementally learn the new/unseen classes to expand the existing model. is is called open-world learning (OWL). is paper proposes a new OWL method based on meta-learning. e key novelty is that the model maintains only a dynamic set of seen classes that allows new classes to be added or deleted with no need for model re-training. Each class is represented by a small set of training examples. In testing, the meta-classi er only uses the examples of the maintained seen classes (including the newly added classes) on-the-y for classi cation and rejection. Experimental results with e-commerce product classi cation show that the proposed method is highly e ective 1 .

show abstract

Item categorization in the e-commerce domain

Cited by 21 publications

References 9 publications

Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce

Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce

Large-scale item categorization for e-commerce

Open-world Learning and Application to Product Classification

Contact Info

Product

Resources

About