Research at Lexin advances the frontiers of legal technology

Research Areas

Our research blends technologies such as AI & NLP with deep legal and product expertise.

Legal Knowledge Extraction

This research area focuses on extracting useful information and knowledge from vast amounts of legal texts and managing this knowledge efficiently. Research can be directed towards developing advanced search algorithms, knowledge graphs, data creation pipelines and databases specifically tailored for legal texts. Recent research topics include:

  • Legal Search Algorithms
  • Knowledge Graph for Legal Documents
  • Legal Data Management

Artificial Intelligence in Legal

This research area involves developing AI and machine learning models to analyze legal documents, statutes, and court decisions. The work involves using relevant legal data to analyze legal textual entailment, predict outcomes of legal cases, identifying trends in judicial decisions, and foreseeing future legal challenges. Recent research topics include:

  • Knowledge Question & Answering
  • Legal Textual Entailment
  • Legal Text Classification & Summarization

Legal Technology Platforms

This research area involves developing advanced legal research platforms that are tailored to the specific needs of different types of users (lawyers, paralegals, students, or the general public). This involves researching, designing, and implementing legal technology platform products with intuitive user experience. Recent research topics include:

  • Legal Search Generative Experience
  • Paralegal AI Assistant
  • Legal Document Search

Research Publications and News

Keep up with Lexin's latest research

LexID: The Metadata and Semantic Knowledge Graph Construction of Indonesian Legal Document

A wonderful serenity has taken possession of my entire soul, like these sweet mornings of spring which I enjoy with my whole heart. I am alone, and feel the charm of existence in this spot, which was created for the bliss of souls like mine. I am so happy, my dear friend, so absorbed in...
Read More

Extreme Multilabel Text Classification on Indonesian Tax Court Ruling using Single Channel CNN and IndoBERT Embedding

Manual searching for legal basis such as paragraphs, articles, and laws when preparing for a tax court hearing is time-consuming. In this paper, we use extreme multilabel text classification approach to predict paragraphs, articles, and laws relevant to an appeal on the Indonesian Tax Court Ruling documents. Traditional machine learning methods, such as random forest,...
Read More