Publications

Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges

Published in ACM Computing Surveys, Volume 58, Issue 6, 2025

This survey explores foundational concepts related to Natural Language Processing (NLP) in the legal domain, illustrating the unique aspects and challenges of processing legal texts, such as extensive document lengths, complex language, and limited open legal datasets. We provide an overview of NLP tasks specific to legal text, such as Document Summarisation, Named Entity Recognition, Question Answering, Argument Mining, Text Classification, and Judgement Prediction. Furthermore, we analyse both developed legal-oriented language models, and approaches for adapting general-purpose language models to the legal domain. Additionally, we identify sixteen open research challenges, including the detection and mitigation of bias in artificial intelligence applications, the need for more robust and interpretable models, and improving explainability to handle the complexities of legal language and reasoning.

Download Paper

Enhancing Aspect based Sentiment Analysis with ParsBERT in Persian Language

Published in Journal of AI and Data Mining, 2024

This paper aim to amplify the efficiency of language models tailored to the Persian language.

Download Paper

Structural Reliability Analysis of Corroding Steel Bridges Using Random-Field Representation

Published in Maintenance, Safety, Risk, Management and Life Cycle Performance of Bridges, 2018

The functional safety of steel bridges is of great importance for governments and infrastructure managers. This functionality is, however, affected by natural aging and environmental threads such as corrosion. Corrosion can play major role in steel bridge failure; mainly by reducing the thickness of bridge girders or by forming pits on the steel surface which consequently affects the structural integrity of the bridge. In this study, an innovative technique for representation of corrosion has been used when applying a multi-failure reliability analysis method. To this aim, the distribution of corrosion pits is modelled by a 2D random field and then, the generated surface is incorporated with a Monte-Carlo reliability analysis method to predict the service life of in-service steel bridge girders.