Creation of draft summary reports based on transcripts of parliamentary sessions

Transcription and translation

Italy - Senate

Use case ID: 032

Author: Senate of Italy

Date: 12 June 2024 
 

Objective:

Generate summary reports, in the standard style of Senate summary reports, derived from the transcript of a chamber or committee session. 

Actors:

  • Senate users (e.g. documentalists and parliamentary staff)
  • Citizens 

Prerequisites:

  • Basic knowledge of computer tools
  • Access to session transcriptions 

Scenario:

  1. A documentalist selects a transcript of a chamber or committee session.
  2. The documentalist invokes a generative AI service to process the transcript.
  3. The AI system generates a draft summary report based on the transcript.
  4. The documentalist reviews and finalizes the summary report for accuracy and completeness. 

Alternate flows:

  • If the AI-generated summary contains errors or omissions, the documentalist manually edits the report to ensure accuracy. 

Expected results:

  • The summary report provides a concise summary proportional to the length of the interventions.
  • The summary preserves significant parts of the text, especially the interventions of the Speaker or chair (of the chamber or committee).
  • The summary clearly indicates the speakers for each intervention. 

Potential challenges:

  • High rate of hallucinations or inaccurate content generation by the AI system
  • Disproportionate summary that either over-condenses or under-summarizes interventions
  • Ensuring the AI system correctly identifies and attributes the speakers 

Data requirements:

  • Accurate and complete transcripts of the session
  • Metadata related to session schedules and speaker lists for better speaker identification 

Integrations with other systems:

  • Parliamentary document management system for storing and retrieving summary reports
  • User authentication system to ensure secure access to AI-generated summaries 

Success metrics:

  • Low rate of AI-generated hallucinations in summary reports
  • User satisfaction scores regarding the accuracy and quality of summaries
  • Reduction in time required to produce summary reports
  • Proportional and accurate summarization of session content 

 

The Use cases for AI in parliaments collection is published by the IPU’s Centre for Innovation in Parliament as part of the Parliamentary Data Science Hub’s project to create guidelines for AI governance in parliaments.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International licence. It may be freely shared and reused with acknowledgement of the author and the IPU. 

A use case describes how a system should work. It is used to plan, develop and measure implementation. A use case is not the same as a case study, which is a descriptive text of an actual project’s implementation. Please note that this use case is provided “as is” and neither the IPU nor the author accepts any responsibility for its use.

For more information about the IPU’s work on artificial intelligence, please visit www.ipu.org/AI or contact [email protected].