TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions

TL;DR

TempRetriever enhances dense passage retrieval by explicitly incorporating temporal information, significantly improving accuracy on time-sensitive question answering datasets through a novel temporal embedding and negative sampling strategy.

Contribution

This paper introduces TempRetriever, a novel temporal-aware dense passage retrieval model that explicitly embeds temporal information, outperforming baseline models on large-scale time-sensitive datasets.

Findings

TempRetriever improves Top-1 accuracy by over 6% on ArchivalQA.

It achieves nearly 10% better Top-1 accuracy on ChroniclingAmericaQA.

A new time-based negative sampling strategy further boosts retrieval performance.

Abstract

Temporal awareness is crucial in many information retrieval tasks, particularly in scenarios where the relevance of documents depends on their alignment with the query's temporal context. Traditional approaches such as BM25 and Dense Passage Retrieval (DPR) focus on lexical or semantic similarity but tend to neglect the temporal alignment between queries and documents, which is essential for time-sensitive tasks like temporal question answering (TQA). We propose TempRetriever, a novel extension of DPR that explicitly incorporates temporal information by embedding both the query date and document timestamp into the retrieval process. This allows retrieving passages that are not only contextually relevant but also aligned with the temporal intent of queries. We evaluate TempRetriever on two large-scale datasets ArchivalQA and ChroniclingAmericaQA demonstrating its superiority over baseline retrieval models across multiple metrics. TempRetriever achieves a 6.63\% improvement in Top-1 retrieval accuracy and a 3.79\% improvement in NDCG@10 compared to the standard DPR on ArchivalQA. Similarly, for ChroniclingAmericaQA, TempRetriever exhibits a 9.56\% improvement in Top-1 retrieval accuracy and a 4.68\% improvement in NDCG@10. We also propose a novel, time-based negative sampling strategy which further enhances retrieval performance by addressing temporal misalignment during training. Our results underline the importance of temporal aspects in dense retrieval systems and establish a new benchmark for time-aware passage retrieval.