AIIRLGOct 24, 2024

Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval

arXiv:2410.18385v223 citationsh-index: 2Has CodeEMNLP
Originality Incremental advance
AI Analysis

This addresses the problem of zero-shot IR for applications lacking historical query data, representing an incremental improvement over existing methods.

The paper tackles the challenge of zero-shot information retrieval in new domains or languages by proposing a Universal Document Linking algorithm that links similar documents to enhance synthetic query generation, achieving state-of-the-art performance across diverse datasets.

Despite the recent advancements in information retrieval (IR), zero-shot IR remains a significant challenge, especially when dealing with new domains, languages, and newly-released use cases that lack historical query traffic from existing users. For such cases, it is common to use query augmentations followed by fine-tuning pre-trained models on the document data paired with synthetic queries. In this work, we propose a novel Universal Document Linking (UDL) algorithm, which links similar documents to enhance synthetic query generation across multiple datasets with different characteristics. UDL leverages entropy for the choice of similarity models and named entity recognition (NER) for the link decision of documents using similarity scores. Our empirical studies demonstrate the effectiveness and universality of the UDL across diverse datasets and IR models, surpassing state-of-the-art methods in zero-shot cases. The developed code for reproducibility is included in https://github.com/eoduself/UDL

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes