Search

The extraction of named entities from court judgments is useful in several downstream applications, such as document anonymization and semantic search engines. In this paper, we discuss the application of named entity recognition and linking (NEEL) to extract entities from Italian civil court judgments. To develop and evaluate our work, we use a corpus of 146 manually annotated court judgments. We use a pipeline that combines a transformer-based Named Entity Recognition (NER) component, a transformer-based Named Entity Linking (NEL) component, and a NIL prediction component. While the NEL and NIL prediction components are not fine-tuned on domain-specific data, the NER component is fine-tuned on the annotated corpus. In addition, we compare different masked language modeling (MLM) adaptation strategies to optimize the result and investigate their impact. Results obtained on a 30-document test set reveal satisfactory performance, especially on the NER task, and emphasize challenges to improve NEEL on similar documents. Our code is available on GitHub.(https://github.com/rpo19/pozzi_aixia_2023. We are not allowed to publish sensitive data and the NER models trained on sensitive data.)

Artificial intelligence’s (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. However, the ensuing excitement has led to negative sentiments, even as AI methods demonstrate remarkable contributions (e.g. in health and genetics). A key factor contributing to this sentiment is the misleading perception that LLMs can effortlessly provide solutions across domains, ignoring their limitations such as hallucinations and reasoning constraints. Acknowledging AI fallibility is crucial to address the impact of dogmatic overconfidence in possibly erroneous suggestions generated by LLMs. At the same time, it can reduce fear and other negative attitudes toward AI. This necessitates comprehensive AI literacy interventions that educate the public about LLM constraints and effective usage techniques, i.e. prompting strategies. With this aim, a pilot educational intervention was performed in a high school with 21 students. It involved presenting high-level concepts about intelligence, AI, and LLMs, followed by practical exercises involving ChatGPT in creating natural educational conversations and applying established prompting strategies. Encouraging preliminary results emerged, including high appreciation of the activity, improved interaction quality with the LLM, reduced negative AI sentiments, and a better grasp of limitations, specifically unreliability, limited understanding of commands leading to unsatisfactory responses, and limited presentation flexibility. Our aim is to explore AI acceptance factors and refine this approach for more controlled future studies.