Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models

Luigi Curini, Alfio Ferrara, Giovanni Pagano, Sergio Picascia

Abstract

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represent a rich yet challenging resource for computational analysis, particularly when preserved only as scanned historical documents.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.

Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models

Abstract

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represent a rich yet challenging resource for computational analysis, particularly when preserved only as scanned historical documents.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.

Paper Structure

This paper contains 17 sections, 1 equation, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Italian Parliamentary Resources
  4. Vision-Language Models
  5. Methodology
  6. Document Acquisition
  7. OCR Extraction
  8. Semantic Labelling
  9. Document Post-Processing
  10. Entity Retrieval
  11. Speaker Matching
  12. Evaluation
  13. Evaluation Setup
  14. OCR Evaluation
  15. Tagging Evaluation
  16. ...and 2 more sections

Figures (3)

  • Figure 1: Pipeline diagram showing the six stages with data flow between components.
  • Figure 2: Excerpt from the stenographic report of the session held on November 27th 1874, Legislature 12 of the Kingdom of Italy. This page excerpt serves as the running example throughout this section.
  • Figure 3: Effect of post-processing on a cross-page speech fragment. Highlighted regions show speaker inference (unknown $\rightarrow$ resolved); underlined text shows hyphenation resolution.