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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hwang, Dae Yon, Taha, Bilal, Pande, Harshit, Nechaev, Yaroslav
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914988032000000
author Hwang, Dae Yon
Taha, Bilal
Pande, Harshit
Nechaev, Yaroslav
author_facet Hwang, Dae Yon
Taha, Bilal
Pande, Harshit
Nechaev, Yaroslav
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2410_18385
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval
Hwang, Dae Yon
Taha, Bilal
Pande, Harshit
Nechaev, Yaroslav
Artificial Intelligence
Information Retrieval
Machine Learning
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
title Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval
topic Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2410.18385