KDD Cup 2022 Workshop:

ESCI Challenge for Improving Product Search

Held in conjunction with KDD'22 Aug 17th, 2022 - Washington D.C., USA


INTRODUCTION

The objective of this workshop is to discuss the winning submissions of the KDDCup 2022 Challenge on improving product search. In this challenge, we introduce the “Shopping Queries Data Set”, a large dataset of difficult search queries, published with the aim of fostering research in the area of semantic matching of queries and products. For each query, the dataset provides a list of up to 40 potentially relevant results, together with ESCI relevance judgements (Exact, Substitute, Complement, Irrelevant) indicating the relevance of the product to the query. Each query-product pair is accompanied by additional information. The dataset is multilingual, as it contains queries in English, Japanese, and Spanish. More details of this challenge are available here; https://www.aicrowd.com/challenges/esci-challenge-for-improving-product-search.

Objective and Tasks

The primary objective of this competition is to build new ranking strategies and, simultaneously, identify interesting categories of results (i.e., substitutes) that can be used to improve the customer experience when searching for products. The three different tasks for this KDD Cup competition using the Shopping Queries Dataset are:
  1. Query-Product Ranking: Given a user specified query and a list of matched products, the goal of this task is to rank the products so that the relevant products are ranked above the non-relevant ones.
  2. Multi-class Product Classification: Given a query and a result list of products retrieved for this query, the goal of this task is to classify each product as being an Exact, Substitute, Complement, or Irrelevant match for the query.
  3. Product Substitute Identification: This task will measure the ability of the systems to identify the substitute products in the list of results for a given query.


SCHEDULE

August 17th, 2022, 1.15PM–5PM (Eastern Standard Time), Washington D.C., USA.

  Opening
  1:15-1:40 PM

Introduction by organizers.  

  Task 1: Query-Product Ranking
  1:40-2:20 PM

  • A Semantic Alignment System for Multilingual Query-Product Retrieval
  • Second place solution of Amazon KDD Cup 2022: ESCI Challenge for Improving Product Search
  • Solution of Team GraphMIRAcles in the KDD Cup 2022 Query-Product Ranking Task
  • A simple but effective solution for Task 1 of KDD Cup 2022 Challenge on improving product search

  Task 2 and 3: Multi-Class and Substitute Product Classification
  2:20-3:00 PM

  • A Winning Solution of KDD CUP 2022 ESCI Challenge for Improving Product Search
  • Some Practice for Improving the Search Results of E-commerce
  • Multiclass Product Classification Based On Multilingual Model and LightGBM (Team:Uni)
  • ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product Search

  Coffee Break
  3:00-3:30 PM
  Poster Session
  3:30-4:00 PM
  All Tasks: Interesting Approaches
  4:00-4:50 PM

  • TFKD Solution for KDD Cup 2022 Amazon Product Search
  • A Boring-yet-effective Approach for the Product Ranking Task of the Amazon KDD Cup 2022
  • CMB AI Lab at KDD Cup 2022 ESCI Task2 and Task3: A Domain Adapted PLM with Context Enhancement for Query-Product Classification
  • A Multi-model Fusion Approach for Product Classification and Product Substitute Identification on Shopping Queries Data
  • KDD Cup 2022 Multiclass Product Classification: Team MetaSoul Solution
  • Predicting Query-Item Relationship using Adversarial Training and Robust Modeling Techniques

  Closing
  4:50-5:00 PM

Concluding remarks by organizers.


SUBMISSION GUIDELINES

The objective of this workshop is to discuss the winning submissions of the Submissions to the Amazon KDD Cup 2022 is single-blind (author names and affiliations should be listed). Everyone in the Top-10 leaderboard submissions will have a guaranteed opportunity for an in-person oral/poster presentation. Other submissions will be evaluated by a committee based on their novelty and insights. The deadline for the submissions is July 31st, 2022 11.59 PM (Anywhere on Earth time). Accepted submissions will be notified latest by August 7th, 2022. Please note that the KDD Cup workshop will have no proceedings and the authors retain full rights to submit or post the paper at any other venue.
Link to the submission website: https://easychair.org/conferences/?conf=amazonkddcup2022

Submissions are limited to a maximum of four (4) pages, including all content and references, and must be in PDF format. Please use ACM Conference templates (two column format). One recommended setting for Latex file is: \documentclass[sigconf, review]{acmart}. Template guidelines are here: https://www.acm.org/publications/proceedings-template.

In addition, authors can provide an optional one page supplement at the end of their submitted paper (it needs to be in the same PDF file) focused on reproducibility. After the submission deadline, the names and order of authors cannot be changed. The paper organization can loosely follow the following format:

    Paper Title and Author Details
  • Abstract
  • Introduction
  • Related Work
  • Model Architecture
  • Results
  • Discussion
  • Conclusion
  • References


ACCEPTED PAPERS

A Winning Solution of KDD CUP 2022 ESCI Challenge for Improving Product Search
  Task 1   Task 2   Task 3
Authors: Jinzhen Lin, Lanqing Xue, Zhenzhe Ying, Changhua Meng, Weiqiang Wang, Haotian Wang and Xiaofeng Wu.

Some Practice for Improving the Search Results of E-commerce
 Task 1   Task 2   Task 3
Authors: Fanyou Wu, Yang Liu, Rado Gazo, Benes Bedrich and Xiaobo Qu.

Multiclass Product Classification Based On Multilingual Model and LightGBM (Team:Uni)
  Task 2   Task 3
Authors: Peng Zhang, Linghan Zheng, Ruiqing Yan, Changyu Li, Rui Hu, Sheng Zhou, Jinrong Jiang, Lian Zhao, Qianjin Guo and Qiang Liu.

A Semantic Alignment System for Multilingual Query-Product Retrieval
  Task 1
Authors: Qi Zhang, Zijian Yang, Yilun Huang, Ze Chen, Zijian Cai, Kangxu Wang, Jiewen Zheng, Jiarong He and Jin Gao.

Second place solution of Amazon KDD Cup 2022: ESCI Challenge for Improving Product Search
  Task 1  Task 2  Task 3
Authors: Xiaolei Qin, Nan Liang, Hongbo Zhang, Wuhe Zou and Weidong Zhang.

ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product Search
 Task 1  Task 2  Task 3
Authors: Xuange Cui, Wei Xiong and Songlin Wang.

Solution of Team GraphMIRAcles in the KDD Cup 2022 Query-Product Ranking Task
 Task 1
Authors: Hanzhu Chen, Zhihao Shi, Zhanqiu Zhang and Jie Wang.

CMB AI Lab at KDD Cup 2022 ESCI Task2 and Task3: A Domain Adapted PLM with Context Enhancement for Query-Product Classification
 Task 2  Task 3
Authors: Haobo Yang, Shiding Fu, Guidong Zheng, Junjie Wen, Jinlong Li and Xing Zhao.

A simple but effective solution for Task 1 of KDD Cup 2022 Challenge on improving product search
 Task 1
Authors: Jinrui Liang, Yali Shangguan and Zhaohao Liang.

A Multi-model Fusion Approach for Product Classification and Product Substitute Identification on Shopping Queries Data
 Task 2  Task 3
Authors: Yanbo Wang, Yuhang Guan, Yuming Li, Hui Qin, Sheng Chen, Shilei Shan, Xuan Yang, Jie Shi and Siyi Wang.
TFKD Solution for KDD Cup 2022 Amazon Product Search
 Task 1
Authors: Cheng Hsu.

KDD Cup 2022 Multiclass Product Classification: Team MetaSoul Solution
 Task 2
Authors: Zhichao Feng, Jiawei Lu, Junwei Cheng, Ke Hou, Kaiyuan Li, Pengfei Wang and Yadong Zhu.

Predicting Query-Item Relationship using Adversarial Training and Robust Modeling Techniques
 Task 3
Authors: Min Seok Kim.

A Boring-yet-effective Approach for the Product Ranking Task of the Amazon KDD Cup 2022
 Task 1
Authors: Vitor Jeronymo, Guilherme Rosa, Surya Kallumadi, Rodrigo Nogueira and Roberto Lotufo.

DATA

The data and its license is available at the following link.
https://github.com/amazon-research/esci-code
If you plan to use this dataset for your own research, please cite this paper.

@article{reddy2022shopping,
title={Shopping Queries Dataset: A Large-Scale {ESCI} Benchmark for Improving Product Search},
author={Chandan K. Reddy and Lluís Màrquez and Fran Valero and Nikhil Rao and Hugo Zaragoza and Sambaran Bandyopadhyay and Arnab Biswas and Anlu Xing and Karthik Subbian},
year={2022},
eprint={2206.06588},
archivePrefix={arXiv}
}