Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
Open Access
- 26 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 5223-5234
Abstract
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 parameters1.Keywords
All Related Versions
Funding Information
- Strategic Emerging Industry Development Special Funds of Shenzhen (JCYJ20200109113403826)
- Natural Science Foundation of China (62006061)
This publication has 26 references indexed in Scilit:
- Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question AnsweringProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs2019
- OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction2019
- Know What You Don’t Know: Unanswerable Questions for SQuAD2018
- Deep Contextualized Word Representations2018
- Semi-supervised sequence tagging with bidirectional language models2017
- Answering Complex Questions Using Open Information Extraction2017
- Deep Residual Learning for Image Recognition2016
- Neural Machine Translation of Rare Words with Subword Units2016
- WikidataCommunications of the ACM, 2014