Learning-Based Information Extraction to Obtain Prominent Named Entities in Indonesian Court Decision Documents
Bibliographic record
Abstract
The increasing number of cases processed in Indonesian courts has led to a rapid growth in court decision documents, which contain crucial legal information.However, due to their unstructured textual nature, diverse classifications, linguistic variations, and inconsistent document structures, extracting meaningful information from these documents remains a significant challenge.This study presents a comparative analysis of machine learning approaches for information extraction (IE) from Indonesian court decisions in criminal tribunal, employing Conditional Random Fields (CRF), Support Vector Machines (SVM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Bidirectional Encoder Representations from Transformers (BERT).Experimental results demonstrate that CRF outperforms SVM in terms of F1-score (0.65 vs. 0.19), indicating its relative robustness for structured prediction tasks.Meanwhile, Bi-LSTM achieves an accuracy of 0.37, reflecting limitations in handling the linguistic complexity of legal texts.Notably, BERT significantly surpasses all other methods, achieving an outstanding accuracy of 0.96.The superior performance of BERT is attributed to its deep contextualized representation and ability to leverage pre-trained knowledge, making it highly effective for handling domain-specific variability in legal documents.These findings highlight the potential of utilizing BERT-based models for automated legal information extraction to support the development of intelligent legal systems and the independence of judiciary in Indonesia.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".