Topic-DPR: Topic-based Prompts for Dense Passage Retrieval
This work tackles the problem of semantic space collapse in dense retrieval for NLP applications, offering an incremental improvement over existing prompt-based methods.
The paper addresses the issue of semantic space collapse in dense passage retrieval by introducing Topic-DPR, which uses multiple topic-based prompts to improve representation differentiation, resulting in superior performance over previous state-of-the-art methods on two datasets.
Prompt-based learning's efficacy across numerous natural language processing tasks has led to its integration into dense passage retrieval. Prior research has mainly focused on enhancing the semantic understanding of pre-trained language models by optimizing a single vector as a continuous prompt. This approach, however, leads to a semantic space collapse; identical semantic information seeps into all representations, causing their distributions to converge in a restricted region. This hinders differentiation between relevant and irrelevant passages during dense retrieval. To tackle this issue, we present Topic-DPR, a dense passage retrieval model that uses topic-based prompts. Unlike the single prompt method, multiple topic-based prompts are established over a probabilistic simplex and optimized simultaneously through contrastive learning. This encourages representations to align with their topic distributions, improving space uniformity. Furthermore, we introduce a novel positive and negative sampling strategy, leveraging semi-structured data to boost dense retrieval efficiency. Experimental results from two datasets affirm that our method surpasses previous state-of-the-art retrieval techniques.