دورية أكاديمية
Addressing Syntax-Based Semantic Complementation: Incorporating Entity and Soft Dependency Constraints into Metonymy Resolution
العنوان: | Addressing Syntax-Based Semantic Complementation: Incorporating Entity and Soft Dependency Constraints into Metonymy Resolution |
---|---|
المؤلفون: | Siyuan Du, Hao Wang |
المصدر: | Future Internet, Vol 14, Iss 3, p 85 (2022) |
بيانات النشر: | MDPI AG, 2022. |
سنة النشر: | 2022 |
المجموعة: | LCC:Information technology |
مصطلحات موضوعية: | metonymy resolution, entity representation, dependency integration, Information technology, T58.5-58.64 |
الوصف: | State-of-the-art methods for metonymy resolution (MR) consider the sentential context by modeling the entire sentence. However, entity representation, or syntactic structure that are informative may be beneficial for identifying metonymy. Other approaches only using deep neural network fail to capture such information. To leverage both entity and syntax constraints, this paper proposes a robust model EBAGCN for metonymy resolution. First, this work extracts syntactic dependency relations under the guidance of syntactic knowledge. Then the work constructs a neural network to incorporate both entity representation and syntactic structure into better resolution representations. In this way, the proposed model alleviates the impact of noisy information from entire sentences and breaks the limit of performance on the complicated texts. Experiments on the SemEval and ReLocaR dataset show that the proposed model significantly outperforms the state-of-the-art method BERT by more than 4%. Ablation tests demonstrate that leveraging these two types of constraints benefits fine pre-trained language models in the MR task. |
نوع الوثيقة: | article |
وصف الملف: | electronic resource |
اللغة: | English |
تدمد: | 1999-5903 |
Relation: | https://www.mdpi.com/1999-5903/14/3/85; https://doaj.org/toc/1999-5903 |
DOI: | 10.3390/fi14030085 |
URL الوصول: | https://doaj.org/article/93125898203c419886971124391b6a6d |
رقم الأكسشن: | edsdoj.93125898203c419886971124391b6a6d |
قاعدة البيانات: | Directory of Open Access Journals |
كن أول من يترك تعليقا!