Knowledge-enhanced event relation extraction via event ontology prompt

Zhuang, Ling; Fei, Hao; Hu, Ping

doi:10.1016/j.inffus.2023.101919

Cited by 2 publications

(1 citation statement)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extraction of semantic relationships between entity pairs from text is a focal point of interest within the information extraction community (Mintz et al 2009;Fei, J. Li, et al 2022;, characterized as a categorization challenge upon specification of entity pairs (Jingye Li et al 2021;Fei, Ren, and Ji 2020a;Wang et al 2022;Miwa and Bansal 2016;Fei, Ren, and Ji 2020b). While traditional supervised techniques depend on extensive manual annotation, limiting their scope to specific domains, distant supervision has attracted considerable attention for its ability to harness self-generated training corpora (Liu et al 2023;Zhuang, Fei, and Hu 2023;Mintz et al 2009;Cao et al 2022), pushing the envelope in relation extraction (RE) performances.…”

Section: Introductionmentioning

confidence: 99%

Semantic Relational Extraction via Learning Syntactic Structural Representation

Éric,

Ari

2023

Preprint

View full text Add to dashboard Cite

Leveraging distant supervision for relation extraction has emerged as a robust method to harness large text corpora, widely adopted to unearth new relational facts from unstructured text. Prevailing neural approaches have made significant strides in relation extraction by representing sentences in compact, low-dimensional vectors. However, the incorporation of syntactic nuances when modeling entities remains underexplored. Our study introduces a novel method for crafting syntax-aware entity embeddings to boost neural relation extraction. We start by encoding entity contexts within dependency trees through tree-GRU to generate sentence-level entity embeddings. We then apply both intra-sentence and inter-sentence attention mechanisms to distill entity embeddings at the sentence set level, considering every occurrence of the pertinent entity pair. The culmination of our methodology is the fusion of sentence and entity embeddings for relation classification. Our experiments on a benchmark dataset indicate that our approach harnesses the full potential of informative instances, thereby setting new benchmarks for relation extraction performance.

show abstract