KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking

• URL: http://arxiv.org/abs/2504.15135v1
• Date: Mon, 21 Apr 2025 14:38:44 GMT
• Title: KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking
• Authors: Juyeon Kim, Geon Lee, Taeuk Kim, Kijung Shin,
• Abstract summary: KGMEL is a novel framework that leverages knowledge-graph triples to enhance entity linking.<n>It operates in three stages: generation,trieval, andranking.<n>Experiments on benchmark datasets demonstrate that KGMEL outperforms existing methods.
• Score: 26.524285614676188
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Entity linking (EL) aligns textual mentions with their corresponding entities in a knowledge base, facilitating various applications such as semantic search and question answering. Recent advances in multimodal entity linking (MEL) have shown that combining text and images can reduce ambiguity and improve alignment accuracy. However, most existing MEL methods overlook the rich structural information available in the form of knowledge-graph (KG) triples. In this paper, we propose KGMEL, a novel framework that leverages KG triples to enhance MEL. Specifically, it operates in three stages: (1) Generation: Produces high-quality triples for each mention by employing vision-language models based on its text and images. (2) Retrieval: Learns joint mention-entity representations, via contrastive learning, that integrate text, images, and (generated or KG) triples to retrieve candidate entities for each mention. (3) Reranking: Refines the KG triples of the candidate entities and employs large language models to identify the best-matching entity for the mention. Extensive experiments on benchmark datasets demonstrate that KGMEL outperforms existing methods. Our code and datasets are available at: https://github.com/juyeonnn/KGMEL.

Related papers

• Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models [17.88134311726175]
  We propose a framework to learn and apply quantized codes for each entity, aiming for the seamless integration of Knowledge Graphs with Large Language Models.<n>Experiment results demonstrate that SSQR outperforms existing unsupervised quantized methods, producing more distinguishable codes.<n>The fine-tuned LLaMA2 and LLaMA3.1 also have superior performance on KG link prediction and triple classification tasks.
  arXiv  Detail & Related papers  (2025-01-30T03:40:20Z)
• KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models [55.39134076436266]
  KG-CF is a framework tailored for ranking-based knowledge graph completion tasks.<n> KG-CF leverages LLMs' reasoning abilities to filter out irrelevant contexts, achieving superior results on real-world datasets.
  arXiv  Detail & Related papers  (2025-01-06T01:52:15Z)
• Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion [36.664300900246424]
  Existing embedding-based methods rely solely on triples in the Knowledge Graph. We propose KGR3, a context-enriched framework for KGC. Experiments on widely used datasets demonstrate that KGR3 consistently improves various KGC methods.
  arXiv  Detail & Related papers  (2024-11-12T20:15:58Z)
• Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA [51.3033125256716]
  We model the subgraph retrieval task as a conditional generation task handled by small language models. Our base generative subgraph retrieval model, consisting of only 220M parameters, competitive retrieval performance compared to state-of-the-art models. Our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T15:22:36Z)
• Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models [95.31941227776711]
  We propose MPIKGC to compensate for the deficiency of contextualized knowledge and improve KGC by querying large language models (LLMs) We conducted extensive evaluation of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks.
  arXiv  Detail & Related papers  (2024-03-04T12:16:15Z)
• Contextualization Distillation from Large Language Model for Knowledge Graph Completion [51.126166442122546]
  We introduce the Contextualization Distillation strategy, a plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models to transform compact, structural triplets into context-rich segments. Comprehensive evaluations across diverse datasets and KGC techniques highlight the efficacy and adaptability of our approach.
  arXiv  Detail & Related papers  (2024-01-28T08:56:49Z)
• Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models [42.38563175680914]
  This paper studies how to automatically generate a natural language text that describes the facts in knowledge graph (KG) Considering the few-shot setting, we leverage the excellent capacities of pretrained language models (PLMs) in language understanding and generation.
  arXiv  Detail & Related papers  (2021-06-03T06:48:00Z)
• Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment [100.19568734815732]
  Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. attribute triples can also provide crucial alignment signal but have not been well explored yet. We propose to utilize an attributed value encoder and partition the KG into subgraphs to model the various types of attribute triples efficiently.
  arXiv  Detail & Related papers  (2020-10-07T08:03:58Z)
• Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning [73.0598186896953]
  We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme. In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training.
  arXiv  Detail & Related papers  (2020-04-29T14:22:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.