PROCAT: Product Catalogue Dataset for Implicit Clustering, Permutation Learning and Structure Prediction

Mateusz Maria Jurewicz, Leon Derczynski

Keywords: set-to-sequence, structure prediction, product catalog, product catalogue, product brochure, permutation learning

TL;DR: A set-to-sequence dataset for complex structure prediction based on 1.5M items in real product catalogues, with metrics, benchmarks, and synthetic data generation library.

Abstract: In this dataset paper we introduce PROCAT, a novel e-commerce dataset containing expertly designed product catalogues consisting of individual product offers grouped into complementary sections. We aim to address the scarcity of existing datasets in the area of set-to-sequence machine learning tasks, which involve complex structure prediction. The task's difficulty is further compounded by the need to place into sequences rare and previously-unseen instances, as well as by variable sequence lengths and substructures, in the form of diversely-structured catalogues. PROCAT provides catalogue data consisting of over 1.5 million set items across a 4-year period, in both raw text form and with pre-processed features containing information about relative visual placement. In addition to this ready-to-use dataset, we include baseline experimental results on a proposed benchmark task from a number of joint set encoding and permutation learning model architectures.

URL: https://doi.org/10.6084/m9.figshare.14709507 and https://github.com/mateuszjurewicz/procat

Contribution Process Agreement: Yes

Dataset Url: https://doi.org/10.6084/m9.figshare.14709507

License: The data is made publicly available under the Attribution-NonCommercial-ShareAlike 4.0 International license (CC BY-NC-SA 4.0). The dataset should not be used for commercial purposes.

Author Statement: Yes