Decomposing Complex Queries for Tip-of-the-tongue Retrieval
Kevin Lin, Kyle Lo, Joseph E. Gonzalez, Dan Klein

TL;DR
This paper presents a framework that decomposes complex user queries into clues, routing them to specialized retrievers to improve retrieval accuracy in tip-of-the-tongue scenarios, especially for non-textual content.
Contribution
The work introduces a novel query decomposition approach that enhances retrieval performance for complex, multi-faceted queries in TOT settings by leveraging specialized retrievers and ensembling.
Findings
Up to 7% improvement in Recall@5 over baseline methods.
Effective handling of multi-modal and context-rich queries.
Demonstrated on a large real-world dataset of 14,441 query-book pairs.
Abstract
When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that describe content elements (e.g., book characters or events), information beyond the document text (e.g., descriptions of book covers), or personal context (e.g., when they read a book). This retrieval setting, called tip of the tongue (TOT), is especially challenging for models heavily reliant on lexical and semantic overlap between query and document text. In this work, we introduce a simple yet effective framework for handling such complex queries by decomposing the query into individual clues, routing those as sub-queries to specialized retrievers, and ensembling the results. This approach allows us to take advantage of off-the-shelf retrievers (e.g., CLIP for retrieving images of book covers) or…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques · Multimodal Machine Learning Applications
MethodsContrastive Language-Image Pre-training
