Syntax-based dynamic latent graph for event relation extraction

Zhuang, Ling; Fei, Hao; Hu, Po

doi:10.1016/j.ipm.2023.103469

Cited by 9 publications

(1 citation statement)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The field of NER in NLP has seen significant strides with neural sequence labeling models [Zhuang et al, 2023, Fei et al, 2020a. While these models have traditionally relied on combinations of bidirectional LSTM and CRF [Fei et al, 2020b to achieve peak performance, recent shifts towards leveraging pretrained language models have further pushed the boundaries of what's possible in NER.…”

Section: Introductionmentioning

confidence: 99%

Advancing Named Entity Recognition with Syntax-Aware Attention Mechanisms

Jason,

Neumann,

Adam

2023

Preprint

View full text Add to dashboard Cite

Named entity recognition (NER) stands as a pivotal task in natural language processing (NLP). Recent advancements have considerably enhanced its effectiveness. However, a gap remains in these systems' ability to fully leverage the recursive dynamics of linguistic structures. This study introduces a novel approach, intertwining the recognition of entities with a deeper understanding of linguistic syntax and tree-like structures. Utilizing a Tree-LSTM that operates under the guidance of dependency trees, we capture the intricate syntactic relationships between words. This process is further refined through the dual application of relative and global attention mechanisms. The relative attention zone is on critical words in the context of each evaluated word, whereas global attention identifies keywords throughout the entire sentence. By projecting these attention-modulated features into a tagging space, our model employs a conditional random field classifier to determine entity labels. We discover that our model adeptly highlights verbs that reveal the types of entities, influenced by their syntactic roles within sentences. Our model sets a new benchmark for performance on two prominent datasets, substantiating our approach.

show abstract

Section: Introductionmentioning

confidence: 99%