Pedro Henrique Luz de Araujo's MSc page

[Google Scholar profile | GitHub | CV at Lattes]

Projects and publications

Please follow the links below to see publications, source code, dataset and model parameters:

Sequence-aware multimodal page classification of Brazilian legal documents. IJDAR 2022.
VICTOR: a Dataset for Brazilian Legal Documents Classification. LREC 2020.
Inferring the source of official texts: can SVM beat ULMFiT?. PROPOR 2020.
Topic Modelling Brazilian Supreme Court Lawsuits. JURIX 2020.
LeNER-Br: a Dataset for Named Entity Recognition in Brazilian Legal Text. PROPOR 2018.

MSc dissertation

Title: Domain-specific datasets for document classification and named entity recognition

MSc thesis (8.7 MB)
Slides (4.5 MB)
Bib entry
The viva was held by MS Teams at 4 pm Brasilia time, on Thursday 29th July 2021.
Committee:
- Alexandre Rademaker (IBM Research)
- Thiago de Paulo Faleiros (UnB)
- Luís Paulo F. Garcia (suplente - UnB)

MSc qualification

Title: From Documents to Entities: A journey through Natural Language Processing tasks and domains

MSc qualification report (882KB)
Slides (1.5MB)
The qualification presentation/exam was held by MS Teams on Friday 7th August 2020 (see video below).
Committee:
- Alexandre Rademaker (IBM Research)
- Thiago de Paulo Faleiros (UnB)
- Luís Paulo F. Garcia (suplente - UnB)

Last modified: 03 August 2021