Skip to main content

Generation of draft stenographic reports based on transcripts of parliamentary sessions

Italy - Senate

Use case ID: 033

Author: Senate of Italy

Date: 12 June 2024 
 

Objective:

Generate a draft stenographic report from the transcript of a chamber or committee session, adhering to the Senate’s format and standards. 

Actors:

  • Senate users (e.g. documentalists and clerks)
  • Citizens accessing public records 

Prerequisites:

  • Basic knowledge of computer tools by Senate users
  • Access to transcription data of the session 

Scenario:

  1. A Senate user selects the transcript of a specific chamber or committee session.
  2. The user invokes a generative AI service designed to process the transcript.
  3. The AI system processes the transcript and generates a draft stenographic report that conforms to the Senate’s format and standards.
  4. The user reviews the AI-generated report for accuracy and format compliance, making adjustments as necessary. 

Alternate flows:

  • If the AI-generated report contains significant errors or is incomplete, the documentalist can manually edit the report or reprocess the transcript using the AI service. 

Expected results:

  • The stenographic report accurately reflects the transcript and adheres to the Senate’s structural standards.
  • Efficiency in generating stenographic reports is enhanced, with reduced manual effort. 

Potential challenges:

  • High rate of AI hallucinations (i.e. inaccuracies or fabrications in the generated text)
  • Ensuring the generated report consistently meets the formal and structural standards required by the Senate
  • Handling variations in speech patterns, accents and languages used during sessions 

Data requirements:

  • Accurate and complete transcriptions of parliamentary sessions
  • Historical stenographic reports to train the AI model on the required format and standards 

Integrations with other systems:

  • Integration with the Senate’s transcription system to streamline the selection and processing of session transcripts
  • Potential future integration with other parliamentary documentation systems for broader applicability 

Success metrics:

  • Low rate of hallucinations (inaccurate or fabricated content)
  • High adherence to the structural and formatting standards of the Senate’s stenographic reports
  • User satisfaction scores from Senate documentalists
  • Time saved in generating stenographic reports compared to manual methods 

 

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]