Skip to main content
User Image

Sharefah Ahmed Alghamdi

Assistant Professor

Assistant professor in IT dept

علوم الحاسب والمعلومات
6T107
publication
Conference Paper
2024

A Novel Approach for Root Selection in the Dependency Parsing

Although syntactic analysis using the sequence labeling method is promising, it can be problematic when the labels sequence does not contain a root label. This can result in errors in the final parse tree when the postprocessing method assumes the first word as the root. In this paper, we present a novel postprocessing method for BERT-based dependency parsing as sequence labeling. Our method leverages the root’s part of speech tag to select a more suitable root for the dependency tree, instead of using the default first token. We conducted experiments on nine dependency treebanks from different languages and domains, and demonstrated that our technique consistently improves the labeled attachment score (LAS) on most of them.

more of publication
publications

Although syntactic analysis using the sequence labeling method is promising, it can be problematic when the labels sequence does not contain a root label. This can result in errors in the final…

by Sharefah Ahmed Al-Ghamdi, Hend Al-Khalifa, Abdulmalik AlSalman
2024
publications

With the advent of pre-trained language models, many natural language processing tasks in various languages have achieved great success.

by Sharefah Al-Ghamdi, Hend Al-Khalifa, Abdulmalik Al-Salman
2023
Published in:
Applied Sciences
publications

This paper introduces the first syntactically annotated corpus for Classical Arabic poetry, a morphologically rich ancient Arabic text. The paper describes how the dependency treebank was prepared…

2021