通过结构化知识与统一检索-生成增强多模态多跳问答
Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
AI总结：
本文提出SKURG方法，通过实体中心融合编码器和统一检索-生成解码器解决多模态多跳问答中检索与生成割裂的问题，在MultimodalQA和WebQA上以更少参数超越现有最优模型。
摘要：
多模态多跳问答涉及通过推理来自不同模态的多个输入源来回答问题。现有方法通常分别检索证据，然后使用语言模型基于检索到的证据生成答案，因此未能充分连接候选证据，也无法在检索过程中建模相互依赖的关系。此外，检索与生成的流水线方法在检索性能较低时可能导致生成性能较差。为解决这些问题，我们提出了一种结构化知识与统一检索-生成（SKURG）方法。SKURG采用以实体为中心的融合编码器，利用共享实体对齐来自不同模态的输入源。然后，它使用统一的检索-生成解码器整合中间检索结果以生成答案，并自适应地确定检索步骤的数量。在两个具有代表性的多模态多跳问答数据集MultimodalQA和WebQA上的大量实验表明，SKURG在源检索和答案生成性能上均优于最先进的模型，且参数更少。我们的代码可在https://github.com/HITsz-TMG/SKURG获取。
英文摘要：
Multi-modal multi-hop question answering involves answering a question by reasoning over multiple input sources from different modalities. Existing methods often retrieve evidences separately and then use a language model to generate an answer based on the retrieved evidences, and thus do not adequately connect candidates and are unable to model the interdependent relations during retrieval. Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low. To address these issues, we propose a Structured Knowledge and Unified Retrieval-Generation (SKURG) approach. SKURG employs an Entity-centered Fusion Encoder to align sources from different modalities using shared entities. It then uses a unified Retrieval-Generation Decoder to integrate intermediate retrieval results for answer generation and also adaptively determine the number of retrieval steps. Extensive experiments on two representative multi-modal multi-hop QA datasets MultimodalQA and WebQA demonstrate that SKURG outperforms the state-of-the-art models in both source retrieval and answer generation performance with fewer parameters. Our code is available at https://github.com/HITsz-TMG/SKURG.
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。
