Robotics & Machine Learning Daily News2024,Issue(Feb.5) :2-3.DOI:10.20965/jaciii.2024.p0179

Reports on Computational Intelligence Findings from Ningbo University Provide New Insights (Semantic Similarity Analysis via Syntax Dependency Structure and Gate Recurrent Unit)

Robotics & Machine Learning Daily News2024,Issue(Feb.5) :2-3.DOI:10.20965/jaciii.2024.p0179

Reports on Computational Intelligence Findings from Ningbo University Provide New Insights (Semantic Similarity Analysis via Syntax Dependency Structure and Gate Recurrent Unit)

扫码查看

Abstract

Fresh data on computational intelligence are presented in a new report. According to news reporting from Zhejiang, People's Republic of China, by NewsRx journalists, research stated, “Sentences are composed of words, phrases, and clauses. The relationship between them is usually tree- like.” Our news correspondents obtained a quote from the research from Ningbo University: “In the hierarchical structure of the sentence, the dependency relationships between different components affect the syntactic structure. Syntactic structure is very important for understanding the meaning of the whole sentence. However, the gated recursive unit (GRU) models cannot fully encode hierarchical syntactic dependencies, which leads to its poor performance in various natural language tasks. In this paper, a model called relative syntactic distance bidirectional gated recursive unit (RSD-BiGRU) is constructed to capture syntactic structure dependencies. The model modifies the gating mechanism in GRU through relative syntactic distance. It also offers a transformation gate to model the syntactic structure more directly. Embedding sentence meanings with sentence structure dependency into dense vectors.”

Key words

Ningbo University/Zhejiang/People's Republic of China/Asia/Computational Intelligence/Machine Learning

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
参考文献量1
段落导航相关论文