posted by organizer: skallumadi || 2250 views || tracked by 1 users: [display]

SIGIR eCom DC 2020 : The 2020 SIGIR Ecom Data Challenge : Multi-modal Product Data Classification and Retrieval challenge

FacebookTwitterLinkedInGoogle

Link: https://sigir-ecom.github.io/data-task.html
 
When Jul 30, 2020 - Jul 30, 2020
Where Xi'an
Abstract Registration Due Jul 15, 2020
Submission Deadline Jul 22, 2020
Notification Due Jul 23, 2020
Final Version Due Jul 27, 2020
Categories    ecommerce   NLP   information retrieval   classification
 

Call For Papers

Call for Participation

The 2020 SIGIR workshop on eCommerce is hosting the Rakuten Multi-modal Product Data Classification and Retrieval challenge. This challenge focuses on two topics, namely large-scale multi-modal (text and image) classification and cross-modal retrieval. The goal of the multi-modal classification task is to predict each product’s 'type code' as defined in the catalog of Rakuten France. In the cross-modal retrieval task, presented with the text of the products, the goal is to retrieve the images corresponding to the products.

Challenge website: https://sigir-ecom.github.io/data-task.html

Important Dates:
Data Challenge opens: April 20, 2020
Final Leaderboard - July 22, 2020
SIGIR eCom Full day Workshop - July 30, 2020

Task Description:

The cataloging of product listings through some type of text or image categorization method is a fundamental problem for any e-commerce marketplace, with applications ranging from personalized search and recommendations to query understanding. Manual and rule-based approaches to categorization are not scalable since commercial products are organized in many and sometimes thousands of classes. When actual users categorize product data, it has often been observed that not only the text of the title and description of the product is useful but also its associated images.

Tasks:

The main tasks for this challenge are as follows:
1. Multi-modal classification. Given a training set of products and their product type codes, predict the corresponding product type codes for an unseen held out test set of products. The systems are free to use the available textual titles and/or descriptions whenever available and additionally the images to allow for true multi-modal learning.
2. Cross-modal retrieval. Given an held-out test set of product items with their titles and (possibly empty) descriptions, predict the best image from among a set of test images that correspond to the products in the test set.

Participation and Data:

The data challenge is open to everyone.

For this challenge, Rakuten France has released approximately 99K product listings in tsv format, including a training (84,916) and test set (13,812). The dataset consists of product titles, product descriptions, product images and their corresponding product type codes. The test set will be released towards the end of the data challenge. Furthermore, one can assume the test set has been generated from the same data distribution as the training set.

Details about evaluation metrics and other aspects of the task can be found at the website: https://sigir-ecom.github.io/data-task.html

Important Dates:
Data Challenge opens: April 20, 2020
Final Leaderboard - July 22, 2020
SIGIR eCom Full day Workshop - July 30, 2020

Related Resources

SIGIR 2020   International ACM SIGIR Conference on Research and Development in Information Retrieval
WSDM 2021   14th ACM Conference on Web Search and Data Mining
AICA 2020   O'Reilly AI Conference San Jose
SIGIR eCom 2020   The 2020 SIGIR Workshop On eCommerce
BDBS 2020   International Conference on Big Data, Blockchain and Security
CHIIR 2020   ACM SIGIR Conference on Human Information Interaction and Retrieval
EACL 2021   The 16th Conference of the European Chapter of the Association for Computational Linguistics
RDAAPS 2021   Reconciling Data Analytics, Automation, Privacy, and Security: A Big Data Challenge
ICWSM-DC 2020   ICWSM Data Challenge
ECIR 2021   European Conference on Information Retrieval