MFBE：利用 FAQ 的多字段信息实现高效稠密检索
MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrieval
AI总结：
本文提出 MFBE 双编码器模型，在训练与推理中组合 FAQ 的问题、答案和类别字段，以低标注成本提升实时语义检索，top-1 准确率最高提升约27%。
摘要：
在 NLP 的问答领域中，常见问题（FAQ）检索是一个重要的子领域，已得到充分研究，并已针对多种语言开展工作。在此场景下，为响应用户查询，检索系统通常会从知识库中返回相关的 FAQ。此类系统的效果取决于其实时建立查询与 FAQ 之间语义匹配的能力。由于查询与 FAQ 之间固有的词汇差距、FAQ 标题缺乏足够上下文、标注数据稀缺以及检索延迟较高，该任务颇具挑战性。在本文中，我们提出了一种基于双编码器的查询-FAQ 匹配模型，该模型在模型训练和推理期间均利用 FAQ 字段（如问题、答案和类别）的多种组合。我们提出的 Multi-Field Bi-Encoder（MFBE，多字段双编码器）模型受益于多个 FAQ 字段所带来的额外上下文，即使在标注数据极少的情况下也表现良好。我们在专有数据集和开源公共数据集上，通过无监督与有监督设置下的实验，从实证上支持了这一主张。在内部数据集和开放数据集上，我们的模型在 FAQ 检索任务中的 top-1 准确率分别比表现最佳的基线提高约 27% 和 20%。
英文摘要：
In the domain of question-answering in NLP, the retrieval of Frequently Asked Questions (FAQ) is an important sub-area which is well researched and has been worked upon for many languages. Here, in response to a user query, a retrieval system typically returns the relevant FAQs from a knowledge-base. The efficacy of such a system depends on its ability to establish semantic match between the query and the FAQs in real-time. The task becomes challenging due to the inherent lexical gap between queries and FAQs, lack of sufficient context in FAQ titles, scarcity of labeled data and high retrieval latency. In this work, we propose a bi-encoder-based query-FAQ matching model that leverages multiple combinations of FAQ fields (like, question, answer, and category) both during model training and inference. Our proposed Multi-Field Bi-Encoder (MFBE) model benefits from the additional context resulting from multiple FAQ fields and performs well even with minimal labeled data. We empirically support this claim through experiments on proprietary as well as open-source public datasets in both unsupervised and supervised settings. Our model achieves around 27% and 20% better top-1 accuracy for the FAQ retrieval task on internal and open datasets, respectively over the best performing baseline.
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。
