QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval
This addresses dense retrieval challenges for information retrieval systems, offering an incremental improvement by augmenting texts rather than changing core methodologies.
The paper tackles information loss and noise in dense retrieval by introducing QAEA-DR, a text augmentation framework that uses LLMs to generate question-answer pairs and event-driven representations, improving retrieval accuracy without modifying embedding models.
In dense retrieval, embedding long texts into dense vectors can result in information loss, leading to inaccurate query-text matching. Additionally, low-quality texts with excessive noise or sparse key information are unlikely to align well with relevant queries. Recent studies mainly focus on improving the sentence embedding model or retrieval process. In this work, we introduce a novel text augmentation framework for dense retrieval. This framework transforms raw documents into information-dense text formats, which supplement the original texts to effectively address the aforementioned issues without modifying embedding or retrieval methodologies. Two text representations are generated via large language models (LLMs) zero-shot prompting: question-answer pairs and element-driven events. We term this approach QAEA-DR: unifying question-answer generation and event extraction in a text augmentation framework for dense retrieval. To further enhance the quality of generated texts, a scoring-based evaluation and regeneration mechanism is introduced in LLM prompting. Our QAEA-DR model has a positive impact on dense retrieval, supported by both theoretical analysis and empirical experiments.