Automatic Annotation of Enhanced Universal Dependencies for Brazilian Portuguese
Open Access
- 17 November 2024
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 217-226
Abstract
This paper presents the first attempt to automatically annotate Enhanced Universal Dependencies for Brazilian Portuguese. We use a symbolic annotation system, based on graph rewriting rules, and modify its original rules to better suit the linguistic characteristics of Portuguese using a manually annotated sample from the journalistic portion of Porttinari treebank as ground truth. Our objective is to assess the performance of the automatic annotation for a novel language and to determine the extent of possible improvements through rule modifications. Results demonstrate significant performance enhancements, where linguistic-driven rule adjustments improved the annotation accuracy 11.38 points, achieving 96.05% F1-score.Keywords
This publication has 12 references indexed in Scilit:
- Investigating the Impact of Syntax-Enriched Transformers on Quantity Extraction in Scientific Texts2023
- DptOIE: a Portuguese open information extraction based on dependency analysisArtificial Intelligence Review, 2022
- Multi-Head Self-Attention Transformation Networks for Aspect-Based Sentiment AnalysisIEEE Access, 2021
- Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees2021
- TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning2021
- Graph Rewriting for Enhanced Universal Dependencies2021
- From Raw Text to Enhanced Universal Dependencies: The Parsing Shared Task at IWPT 20212021
- LIMIT-BERT : Linguistics Informed Multi-Task BERT2020
- Overview of the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies2020
- Supporting the adaptation of texts for poor literacy readers2009