The 3rd International Workshop on
Interactive and Scalable Information Retrieval METHODS FOR e-COMMERCE
(ISIR-eCom 2024)
Held in conjunction with WSDM - March 8th, 2024
Register

Visits: web counter

Introduction

Over the past few years, consumer behavior has shifted from traditional in-store shopping to online shopping. For example, eCommerce sales have grown from around 5% of total US sales in 2012 to around 15.4% in year 2023. This rapid growth of eCommerce has created new challenges and vital new requirements for intelligent information retrieval systems.

Scalable systems

Since the pandemic hit, eCommerce became an important part of people’s routine and they started using online shopping for smallest grocery items to big electronics as well as cars. With such a large assortment of products and millions of users, achieving higher scalability without losing accuracy is a leading concern for information retrieval systems for eCommerce.

Interactive Systems

The diverse buyers make the relevance of the results highly subjective, because relevance varies for different buyers. The most suitable and intuitive solution to this problem is to make the system interactive and provide correct relevance for different users. Hence, interactive information retrieval systems are becoming necessity in eCommerce.

System improvement

To handle sudden change in buyers’ behavior, industries adopted existing sub-optimal in- formation retrieval techniques for various eCommerce tasks. Parallelly, they also started exploring/researching for better solutions and in dire need of help from research community

The objective of this workshop is to bring a diverse set of practitioners and researchers together and encourage them to share their ideas, challenges & solutions and research. This workshop will provide a forum to discuss and learn the latest trends for interactive and scalable information retrieval approaches for eCommerce.

This workshop will provide a forum to discuss and learn the latest trends for interactive and scalable information retrieval approaches for eCommerce. It will provide academic and industrial researchers a platform to present their latest works, share research ideas, present and discuss various challenges, and identify the areas where further research is needed. It will foster the development of a a research community focused on solving eCommerce-related information retrieval problems that provide superior eCommerce experience to all users.

Topics of interest include, but are not limited to:

    • LLMs in eCommerce
      • Conversational Search using LLMs
      • LLMs for intent understanding
      • Model distillation from LLMs for eCommerce
      • Attribute extraction using LLMs
      • Label generation for eCommerce
    • Query Understanding
      • Type-ahead/auto-completion, spell correction
      • LLMs for overall query understanding
      • Non-text query understanding
      • Attribute understanding
      • Implicit query intent understanding
    • Product Understanding
      • Product intent and facets
      • Product knowledge graph
      • Product review summary using LLMs
      • Ontology mining for product graph construction
    • Product Retrieval and Ranking
      • Product indexing and recall
      • Scalable and real-time indexing for frequently changing products (offers, auctions, etc.)
      • Recall and Ranking for multi-faceted products and multi-attributed queries
      • Ranking for Relevance vs Popularity vs Business trade-offs
      • Search Re-Ranking
    • Personalization and Recommendation
      • Interactive Search for personalization
      • Product Question Answering
      • Context and/or location based personalization
      • User attribute based personalization
      • Personalized and Semantic Retrieval
      • LLMs for recommendations
    • Conversational Search and Recommendation
      • Multi-turn product search and recommendation
      • Conversational query understanding and re-writing
      • Clarification and preference elicitation
      • Conversational result presentation and explanation
    • Cross-domain learning
      • Transfer learning for NLP
      • Cross-domain conversational search system
      • Transfer learning for cross-domain product ranking
      • Multi-modal conversational systems for eCommerce
    • Other Topics
      • Feature learning for eCommerce search
      • Search & Recommendations: Fairness and trust for marketplaces
      • Balancing sponsorship vs relevance tread off in search results
      • Robust training objective and effective experimental strategy for IR models
      • End-to-End solution for interactive and scalable search framework

Call for Papers

Download CFP

All papers will be peer reviewed (single-blind) by the program committee and judged by their relevance to the workshop, especially to the main themes identified above, and their potential to generate discussion.

All submissions must be in PDF format according to the latest ACM template published in the ACM guidelines (two column format). Please select the generic “sigconf” sample and for blind manuscript submission recommended setting for Latex file of manuscript is: \documentclass[sigconf, anonymous, review]{acmart}. The PDF files must have all non-standard fonts embedded. Submissions must describe work that is not previously published, and not currently under review elsewhere. All submissions must be in English. We invite you all to contribute: full research papers (up to 10+2 pages) and short papers (up to 5+1 pages). Full workshop papers should not exceed 12 pages in length (maximum 8 pages for the main paper content + maximum 2 pages for appendixes + maximum 2 pages for references).

Please note that at least one of the authors of each accepted paper must register to WSDM conference to present the paper during the ISIR-eCom 2024 workshop.

Submissions to ISIR-eCom 2024 workshop should be made at easychair.

Key Dates

2024
Submissions Due Jan 15 Jan 22
Notification Feb 01
Camera Ready Version Due Feb 23
Workshop Day March 08


Schedule

Time Talk Title
9:00am - 9:15am Opening Remarks Welcome to ISIR-eCom
9:15am - 10:00am Invited Talk 1 - Ching-Wei Chen Real-world Applications of LLMs for eCommerce.
Coffee Break
10:30am - 11:15am Invited Talk 2 - Mahashweta Das Machine Learning for Financial Transaction Data: A Recommendation Use Case.
11:15am - 12:00pm Invited Talk 3 - Prof. Pan Li Dual Learning: Bridging Knowledge Between LLM and Recommender System.
Lunch Break
01:30pm - 02:15pm Invited Talk 3 - Luna Dong Generations of Knowledge Graphs: The Crazy Ideas and The Business.
02:15pm - 02:30pm Paper 1 Captions Are Worth a Thousand Words: Enhancing Product Retrieval with Pretrained Image-to-Text Models.
02:30pm - 02:45pm Paper 2 Point-of-interest Re-ranking by Modeling Session Context and Geography-semantics Interaction.
02:45pm - 03:00pm Paper 3 DeepMMATE: Deep learning based MultiModal architecture for Audit Taxability classification with XAI.
03:00pm - 03:15pm Paper 4 CAPS: A Practical Partition Index for Filtered Similarity Search.
3:15pm - 3:30pm Paper 5 Multi-objective Neural Retrieval for Query AutoComplete.
03:30pm - 03:05pm Closing Notes

Registration

Register at WSDM 2024

Invited Speakers

 

Luna Dong

Principal Scientist
Meta Reality Labs, CA
 

Ching-Wei Chen

Vice President
Crossing Minds, CA
 

Pan Li

Assistant Professor
Georgia Institute of Technology, GA
 

Mahashweta Das

Senior Director
Visa Research, CA
 

Speaker Title
Luna Dong Generations of Knowledge Graphs: The Crazy Ideas and The Business [presentation] [Abstract]

Ching-Wei Chen Real-world Applications of LLMs for eCommerce [presentation] [Abstract]

Prof. Pan Li Dual Learning: Bridging Knowledge Between LLM and Recommender System [presentation] [Abstract]

Mahashweta Das Machine Learning for Financial Transaction Data: A Recommendation Use Case [Abstract]

Accepted Papers

  1. Captions Are Worth a Thousand Words: Enhancing Product Retrieval with Pretrained Image-to-Text Models [presentation] [BibTex]
    Authors: Jason Tang, Garrin McGoldrick, Marie Al-Ghossein and Ching-Wei Chen.

  2. Point-of-interest Re-ranking by Modeling Session Context and Geography-semantics Interaction [presentation] [BibTex]
    Authors: Lang Mei, Jiaxin Mao and Ji-rong Wen.

  3. DeepMMATE: Deep learning based MultiModal architecture for Audit Taxability classification with XAI [presentation] [BibTex]
    Author: Harish Y V S.

  4. CAPS: A Practical Partition Index for Filtered Similarity Search [presentation] [BibTex]
    Authors: Gaurav Gupta, Jonah Wonkyu Yi, Benjamin Coleman, Vihan Lakshman, Chen Luo and Anshumali Shrivastava.

  5. Multi-objective Neural Retrieval for Query AutoComplete [presentation] [BibTex]
    Authors: Rohit Patki, Sravan Bodapati and Chris Potts.

Workshop Organizers

 

Vachik Dave

Walmart Global Tech
Sunnyvale, CA
 

Linsey Pang

Salesforce
San Francisco, CA
 

Xiquan Cui

The Home Depot
Atlanta, GA
 

Chen Luo

Amazon
Seattle, WA
 

 

Hamed Zamani

University of Massachusetts Amherst
Amherst, ‎MA

Lingfei Wu

Pinterest
New York, NY
 

George Karypis

University of Minnesota Twin Cities
MN

PC members

  • Aashish Jain, Salseforce
  • Rishi Bhatia, LLM4AI program
  • Monika Shrivastav, Walmart Global Tech
  • Chenhao Fang, Walmart Global Tech

Contact us

Please send questions and enquiries to isir.ecom.workshop@gmail.com.

 
Copyright © 2024