This paper explores the task of automatic prediction of text spans in a legal problem description that support a legal area label. We use a corpus of problem descriptions written by laypeople in English that is annotated by practising lawyers. Inherent subjectivity exists in our task because legal area categorisation is a complex task, and lawyers often have different views on a problem, especially in the face of legally-imprecise descriptions of issues. Experiments show that training on majority-voted spans outperforms training on disaggregated ones.

Cross-lingual transfer learning has proven useful in a variety of Natural Language Processing (NLP) tasks, but it is understudied in the context of legal NLP, and not at all in Legal Judgment Prediction (LJP). We explore transfer learning techniques on LJP using the trilingual Swiss-Judgment-Prediction dataset, including cases written in three languages. We find that cross-lingual transfer improves the overall results across languages, especially when we use adapter-based fine-tuning. Finally, we further improve the model's performance by augmenting the training dataset with machine-translated versions of the original documents, using a 3x larger training corpus. Further on, we perform an analysis exploring the effect of cross-domain and cross-regional transfer, i.e., train a model across domains (legal areas), or regions. We find that in both settings (legal areas, origin regions), models trained across all groups perform overall better, while they also have improved results in the worst-case scenarios. Finally, we report improved results when we ambitiously apply cross-jurisdiction transfer, where we further augment our dataset with Indian legal cases.

Artificial intelligence (AI) has the potential to help every sector of the economy. There is a challenge, though, in sectors that have fuzzier analysis and the potential to train with data that can continue human biases. A couple of years ago, I described the problem with bias in an article about machine learning (ML) applied to criminal recidivism. It's worth revisiting the sector as time have changed in how bias is addressed. One way is to look at sectors in the legal profession where bias is a much smaller factor.

Some areas of AI are further along in adoption than others. One of those areas is in recruiting. Already, there are companies that are marketing services to review hundreds (or thousands) of applicants and give each candidate a "score" based on multiple factors.The potential pitfall is that the output from some of these systems may have a disparate impact on a protected group. The most notable example was a system being developed (and rejected) by Amazon that did not like women. Thus, HR needs to have a seat at the table when these systems are being considered.