Sequence-to-Sequence Models for Extracting Information from Registration and Legal Documents

Abstract

A typical information extraction pipeline consists of tokenor span-level classification models coupled with a series of pre-and postprocessing scripts. In a production pipeline, requirements often change, with classes being added and removed, which leads to nontrivial modifications to the source code and the possible introduction of bugs. In this work, we evaluate sequence-to-sequence models as an alternative to token-level classification methods for information extraction of legal and registration documents. We finetune models that jointly extract the information and generate the output already in a structured format. Post-processing steps are learned during training, thus eliminating the need for rule-based methods and simplifying the pipeline. Furthermore, we propose a novel method to align the output with the input text, thus facilitating system inspection and auditing. Our experiments on four real-world datasets show that the proposed method is an alternative to classical pipelines.

Exploring zero-shot models for cross-lingual and cross-domain transfer learning

“…Proceedings of the Eighth International Competition on Legal Information Extraction/Entailment. Finally, although not directly related to this dissertation, the following article (PIRES et al, 2022) was also published over the course of the Master's.…”

“…• Pires, R., Souza, F., Rosa, G., Nogueira, R., Lotufo, R. (2022). Sequence-to-Sequence Models for Extracting Information from Registration and Legal Documents.…”