通过精细伪相关标注的自监督实现密集检索和对话密集检索的领域自适应
Domain Adaptation for Dense Retrieval and Conversational Dense Retrieval through Self-Supervision by Meticulous Pseudo-Relevance Labeling
AI总结：
提出结合查询生成与自监督伪相关标注（使用T5-3B和困难负例）的方法，实现密集检索及对话密集检索的领域自适应，实验证明微调后基线模型性能提升。
摘要：
近期研究表明，密集检索模型在不同分布的目标领域上的泛化能力有限，这与基于交互的模型所取得的结果形成对比。先前解决这一挑战的尝试涉及利用对抗学习和查询生成方法，但两种方法均只带来了有限的改进。本文提出将查询生成方法与自监督方法相结合，在目标领域上自动生成伪相关标签。为此，利用T5-3B模型进行伪正例标注，并精心选择困难负例。我们还将此策略应用于对话密集检索模型以支持对话搜索。采用了类似的伪标签方法，但额外增加了一个查询重写模块，用于重写对话查询以供后续标注。所提出的方法使得模型能够利用目标数据集中的真实查询和文档进行领域自适应。在标准密集检索和对话密集检索模型上的实验均表明，当基线模型在伪相关标注数据上进行微调后，性能得到了提升。
英文摘要：
Recent studies have demonstrated that the ability of dense retrieval models to generalize to target domains with different distributions is limited, which contrasts with the results obtained with interaction-based models. Prior attempts to mitigate this challenge involved leveraging adversarial learning and query generation approaches, but both approaches nevertheless resulted in limited improvements. In this paper, we propose to combine the query-generation approach with a self-supervision approach in which pseudo-relevance labels are automatically generated on the target domain. To accomplish this, a T5-3B model is utilized for pseudo-positive labeling, and meticulous hard negatives are chosen. We also apply this strategy on conversational dense retrieval model for conversational search. A similar pseudo-labeling approach is used, but with the addition of a query-rewriting module to rewrite conversational queries for subsequent labeling. This proposed approach enables a model's domain adaptation with real queries and documents from the target dataset. Experiments on standard dense retrieval and conversational dense retrieval models both demonstrate improvements on baseline models when they are fine-tuned on the pseudo-relevance labeled data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
