Improving Neural Ranking Models with Traditional IR Methods
This provides a cost-effective solution for information retrieval practitioners, though it is incremental as it builds on existing methods.
The paper tackles the high computational and data requirements of neural ranking models by proposing a low-resource alternative combining TF-IDF with shallow embeddings, achieving competitive performance with complex models on three datasets and improving large-scale fine-tuned models.
Neural ranking methods based on large transformer models have recently gained significant attention in the information retrieval community, and have been adopted by major commercial solutions. Nevertheless, they are computationally expensive to create, and require a great deal of labeled data for specialized corpora. In this paper, we explore a low resource alternative which is a bag-of-embedding model for document retrieval and find that it is competitive with large transformer models fine tuned on information retrieval tasks. Our results show that a simple combination of TF-IDF, a traditional keyword matching method, with a shallow embedding model provides a low cost path to compete well with the performance of complex neural ranking models on 3 datasets. Furthermore, adding TF-IDF measures improves the performance of large-scale fine tuned models on these tasks.