Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hei, Lei, Liao, Tingjing, Pei, Yingxin, Qi, Yiyang, Wang, Jiaqi, Li, Ruiting, Ren, Feiliang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908558521532416
author Hei, Lei
Liao, Tingjing
Pei, Yingxin
Qi, Yiyang
Wang, Jiaqi
Li, Ruiting
Ren, Feiliang
author_facet Hei, Lei
Liao, Tingjing
Pei, Yingxin
Qi, Yiyang
Wang, Jiaqi
Li, Ruiting
Ren, Feiliang
contents Relation extraction (RE) aims to identify semantic relations between entities in unstructured text. Although recent work extends traditional RE to multimodal scenarios, most approaches still adopt classification-based paradigms with fused multimodal features, representing relations as discrete labels. This paradigm has two significant limitations: (1) it overlooks structural constraints like entity types and positional cues, and (2) it lacks semantic expressiveness for fine-grained relation understanding. We propose \underline{R}etrieval \underline{O}ver \underline{C}lassification (ROC), a novel framework that reformulates multimodal RE as a retrieval task driven by relation semantics. ROC integrates entity type and positional information through a multimodal encoder, expands relation labels into natural language descriptions using a large language model, and aligns entity-relation pairs via semantic similarity-based contrastive learning. Experiments show that our method achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21151
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction
Hei, Lei
Liao, Tingjing
Pei, Yingxin
Qi, Yiyang
Wang, Jiaqi
Li, Ruiting
Ren, Feiliang
Computation and Language
Information Retrieval
Relation extraction (RE) aims to identify semantic relations between entities in unstructured text. Although recent work extends traditional RE to multimodal scenarios, most approaches still adopt classification-based paradigms with fused multimodal features, representing relations as discrete labels. This paradigm has two significant limitations: (1) it overlooks structural constraints like entity types and positional cues, and (2) it lacks semantic expressiveness for fine-grained relation understanding. We propose \underline{R}etrieval \underline{O}ver \underline{C}lassification (ROC), a novel framework that reformulates multimodal RE as a retrieval task driven by relation semantics. ROC integrates entity type and positional information through a multimodal encoder, expands relation labels into natural language descriptions using a large language model, and aligns entity-relation pairs via semantic similarity-based contrastive learning. Experiments show that our method achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.
title Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2509.21151