Example-Driven Intent Synthesis for Constrained Data Bundle Retrieval: Focused Text Snippet Extraction and Beyond
Whanhee Cho, Kuangfei Long, Mahmood Jasim, Matteo Brucato, Alexandra Meliou, Peter J. Haas, Anna Fariha

TL;DR
Ex2Bundle is a framework that enables users to specify bundle retrieval intent through examples, automatically synthesizing and relaxing queries to improve usability and alignment with user goals.
Contribution
The paper introduces Ex2Bundle, a novel example-driven framework for bundle retrieval that synthesizes and relaxes queries to handle user intent and feasibility issues.
Findings
Ex2Bundle improves usability in bundle retrieval tasks.
It effectively synthesizes queries from user-provided examples.
The framework maintains intent alignment even under data distribution shifts.
Abstract
Selecting a bundle of items that collectively satisfies constraints is a fundamental task across databases, recommender systems, and text summarization. Unlike traditional retrieval that returns individual or top-k items, bundle retrieval is inherently combinatorial and, in general, NP-hard. Although package queries can efficiently retrieve bundles given a well-formed query, two key user-centric challenges remain: (1) expressing and tuning multi-dimensional bundle intent through a user-friendly interface, and (2) ensuring feasibility when the query yields empty results. We introduce Ex2Bundle, an Example-driven Bundle retrieval framework that enables users to specify their intent through example bundles and automatically synthesizes package queries that capture the intent implicit in those example bundles via aggregate constraints. Ex2Bundle also addresses a challenge unique to bundle…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
