Friday, December 1, 2023 | 03:39 WIB

UI Students Create Artificial Intelligence to Test Conformity with Legislation


Jakarta, IO – A team of students from Universitas Indonesia’s Faculty of Computer Science (Fasilkom UI) created artificial intelligence (AI) that can automatically test the alignment between laws and regulations.

Fasilkom UI dean Petrus Mursanto said the achievement was a form of real contribution from Fasilkom UI academics to the nation, per Antara, Tuesday (29/8).

He said that this achievement adds to the series of excellent track records of Fasilkom UI students in the field of information and communication technology at the national level.

“Legal regulations have a central role in regulating the rights and obligations of every citizen,” he said.

However, he said, sometimes disharmony occurs between statutory regulations, such as conflicting contents of regulations that can threaten legal certainty for the citizens.

According to him, efforts to detect and test the alignment of laws and regulations is a complex task, and so far it has been done manually.

“This innovation by the Three Neuron V2 Team can help legislators and policy makers in keeping these laws and regulations in harmony and not colliding with each other,” he said.

He explained that the proposed AI-assisted solution utilizes legal textual entailment (LTE), a sub-field method in natural language processing (NLP) and AI that focuses on determining a logical relationship between two legal texts.

This solution, said Peterus, was implemented using the LawID dataset which was also created by the Three Neuron V2 team for LTE purposes.

“The dataset consists of tens of thousands of data which includes primary data such as laws and regulations, starting from the level of the constitution, laws, to derivative regulations, such as government regulations and ministerial regulations, and includes secondary data such as Constitutional Court decisions,” he said.

In processing and summarizing regulatory documents, said Petrus, the Three Neuron V2 Team used various language models to produce sub topics using the BERTopic technique.

Read: Super Blue Moon Phenomenon To Appear On August 30

One of the models proposed in the experiment, namely BigBird-NLI, has been applied to the primary LTE section of the LawID dataset and managed to achieve an accuracy of 99 percent in validation data after going through a fine-tuning process using 800 paragraph pairs of documents.

The team won first prize in the Ria Statistics competition and the 2023 Data Science Festival (Satria Data) organized by the National Achievement Center in Malang on August 20-24. The team consists of Bryan Tjandra, Nyoo Steven Christopher Handoko and Oey Joshua Jodrian. (rr)


Latest article

Related Articles



Terrorism in Palestine

Quo Vadis, Indonesia? Part I: Museums

The Museum on Fire…

The Coral Triangle Centre

The Transformative Power of Art

A Ukrainian Art Exhibition in Jakarta