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

TL;DR

A novel Universal Document Linking algorithm, which links similar documents to enhance synthetic query generation across multiple datasets with different characteristics, surpassing state-of-the-art methods in zero-shot cases.

Abstract

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

Figures (3)

• Figure 1: Overall zero-shot case. IR model is fine-tuned with synthetic queries, then interacted with user queries.
• Figure 2: Distribution of rank of correctly classified queries when $k$=100 in NFCorpus, SciFact, ArguAna. (a) Single linked query-document. (b) Multiple linked query-documents. Blue line: Median value.
• Figure 3: Grid search for $\gamma$ and $\delta$.