Banca de DEFESA: GISLIANY LILLIAN ALVES DE OLIVEIRA

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
STUDENT : GISLIANY LILLIAN ALVES DE OLIVEIRA
DATE: 29/08/2025
TIME: 09:00
LOCAL: Remoto
TITLE:

A Knowledge Graph-Based Approach for Modeling Legislative Texts: Representation and Document Similarity Analysis

KEY WORDS:

Legislative texts, Natural Language Processing, Knowledge Graphs, Graph-Based AI.

PAGES: 100
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUMMARY:

The most prominent task of the Legislative Branch — lawmaking — depends on a complex and demanding process in which new proposals must be examined, debated, and revised in light of existing legislation. These activities are often human labor-intensive due to the technical language, substantial length, and interdependence of legal texts. At the same time, these characteristics present a tangible opportunity for Artificial Intelligence (AI), particularly through the integration of Natural Language Processing (NLP) and structured data representations. Aiming to model legislative documents in a way that preserves their rich structural semantics, this work proposes an approach for transforming legislative texts into domain-specialized Knowledge Graphs (KGs) that capture their inherent hierarchical organization. Based on LexML standards — a Brazilian XML schema for legal documents — the proposed method extracts explicit structural relationships (e.g., articles, paragraphs, subsections) and organizes them into KGs stored in a Neo4j database. These graphs reflect the internal topology of legal texts, enabling structured representations that support more meaningful analysis than unstructured raw text. To assess the effectiveness of this structure-aware approach, comparative experiments were conducted on document similarity tasks, a core component of legislative workflows. Two scenarios were evaluated: (i) a text-only baseline, using BERT-based sentence embeddings averaged across document sections; and (ii) structure-aware graphs, represented through embeddings generated by FastRP and GraphSAGE. Experiments using legislative proposals from the Legislative Assembly of Rio Grande do Norte (ALRN) show that while the text-based model achieved higher precision, recall, and F1-scores, the KG-based representations provided interpretable, structure-driven insights that complement purely textual models. Finally, the results demonstrate the feasibility of converting legislative documents into Knowledge Graphs, laying the groundwork for future enrichment with contextual information extracted by Large Language Models (LLMs). By bridging NLP and graph-based AI, this work advances methodologies for legal document modeling, offering a reproducible pipeline for document similarity analysis, structural understanding, and improved efficiency in legislative processes.

 

COMMITTEE MEMBERS:
Presidente - 2885532 - IVANOVITCH MEDEIROS DANTAS DA SILVA
Interno - 1153006 - LUIZ AFFONSO HENDERSON GUEDES DE OLIVEIRA
Externo ao Programa - 2249146 - CARLOS MANUEL DIAS VIEGAS - UFRNExterno à Instituição - JUAN MOISES MAURICIO VILLANUEVA - UFPB
Externo à Instituição - THIAGO MEDEIROS BARROS - IFRN