一作ACL 2026Poster· Natural Language Processing
G i LT : Augmenting Transformer Language Models with Dependency Graphs
Tianyu Huang · Yida Zhao · Chuyan Zhou · Kewei Tu
摘要
Augmenting Transformers with linguistic structures effectively enhances the syntactic generalization performance of language models. Previous work in this direction focuses on syntactic tree structures of languages, in particular constituency tree structures. We propose Graph-Infused Layers Trans...