Multi-Perspective Semantic Information Retrieval

TL;DR

This paper introduces a Multi-Perspective IR system that combines various deep learning and traditional models to improve relevance prediction in biomedical information retrieval, evaluated on BioASQ challenges.

Contribution

It proposes a novel multi-perspective approach and a standardized tuning framework for IR systems, enhancing relevance prediction accuracy.

Findings

Improved relevance prediction in biomedical IR tasks.

Effective combination of deep learning and traditional IR models.

Validated performance gains on BioASQ challenges.

Abstract

Information Retrieval (IR) is the task of obtaining pieces of data (such as documents or snippets of text) that are relevant to a particular query or need from a large repository of information. While a combination of traditional keyword- and modern BERT-based approaches have been shown to be effective in recent work, there are often nuances in identifying what information is "relevant" to a particular query, which can be difficult to properly capture using these systems. This work introduces the concept of a Multi-Perspective IR system, a novel methodology that combines multiple deep learning and traditional IR models to better predict the relevance of a query-sentence pair, along with a standardized framework for tuning this system. This work is evaluated on the BioASQ Biomedical IR + QA challenges.