KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding
Knowledge-enhanced methods have bridged the gap between human beings and machines in generating dialogue responses. However, most previous works solely seek knowledge from a single source, and thus they often fail to obtain available knowledge because of the insufficient coverage of a single knowledge source. To this end, infusing knowledge from multiple sources becomes a trend. This paper proposes a novel approach Knowledge Source Aware Multi-Head Decoding, KSAM, to infuse multi-source knowledge into dialogue generation more efficiently. Rather than following the traditional single decoder paradigm, KSAM uses multiple independent source-aware decoder heads to alleviate three challenging problems in infusing multi-source knowledge, namely, the diversity among different knowledge sources, the indefinite knowledge alignment issue, and the insufficient flexibility/scalability in knowledge usage. Experiments on a Chinese multi-source knowledge-aligned dataset demonstrate the superior performance of KSAM against various competitive approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderDialogue GenerationDiversitySimilar Papers 제목 키워드 기반
WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-…
Image-level Supervised Instance Segmentationobject-detectionObject DetectionSegmentation+2Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT
Infusing factual knowledge into pre-trained models is fundamental for many knowledge-intensive tasks. In this paper, we proposed Mixture-of-Partitions (MoP), an infusion approach that can handle a very large knowledge gr…
Knowledge GraphsDarkSAM: Fooling Segment Anything Model to Segment Nothing
Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial…
modelContextGPT: Infusing LLMs Knowledge into Neuro-Symbolic Activity Recognition Models
Context-aware Human Activity Recognition (HAR) is a hot research area in mobile computing, and the most effective solutions in the literature are based on supervised deep learning models. However, the actual deployment o…
Activity RecognitionCommon Sense ReasoningHuman Activity RecognitionPrompt EngineeringFine-tuning vision foundation model for crack segmentation in civil infrastructures
Large-scale foundation models have become the mainstream deep learning method, while in civil engineering, the scale of AI models is strictly limited. In this work, a vision foundation model is introduced for crack segme…
Crack Segmentationparameter-efficient fine-tuningSegmentationSemantic Segmentation