Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models
This work addresses the challenge of accurately processing parliamentary proceedings for computational analysis, though it appears incremental as it builds on existing OCR and entity linking techniques.
The paper tackles the problem of transcribing and analyzing Italian parliamentary speeches from scanned historical documents by proposing a Vision-Language Model pipeline that improves transcription quality and speaker tagging compared to traditional OCR methods.
Parliamentary proceedings represent a rich yet challenging resource for computational analysis, particularly when preserved only as scanned historical documents. Existing efforts to transcribe Italian parliamentary speeches have relied on traditional Optical Character Recognition pipelines, resulting in transcription errors and limited semantic annotation. In this paper, we propose a pipeline based on Vision-Language Models for the automatic transcription, semantic segmentation, and entity linking of Italian parliamentary speeches. The pipeline employs a specialised OCR model to extract text while preserving reading order, followed by a large-scale Vision-Language Model that performs transcription refinement, element classification, and speaker identification by jointly reasoning over visual layout and textual content. Extracted speakers are then linked to the Chamber of Deputies knowledge base through SPARQL queries and a multi-strategy fuzzy matching procedure. Evaluation against an established benchmark demonstrates substantial improvements both in transcription quality and speaker tagging.