BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//speaker//8S77NV
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-berlin-2023-HMGCPL@pretalx.com
DTSTART;TZID=CET:20230418T144500
DTEND;TZID=CET:20230418T153000
DESCRIPTION:Local Planning Authorities (LPAs) in the UK rely on written rep
 resentations from the community to inform their Local Plans which outline 
 development needs for their area. With an average of 2000 representations 
 per consultation and 4 rounds of consultation per Local Plan\, the volume 
 of information can be overwhelming for both LPAs and the Planning Inspecto
 rate tasked with examining the legality and soundness of plans. In this st
 udy\, we investigate the potential for Large Language Models (LLMs) to str
 eamline representation analysis.\n\nWe find that LLMs have the potential t
 o significantly reduce the time and effort required to analyse representat
 ions\, with simulations on historical Local Plans projecting a reduction i
 n processing time by over 30%\, and experiments showing classification acc
 uracy of up to 90%. \n\nIn this presentation\, we discuss our experimental
  process which used a distributed experimentation environment with Jupyter
  Lab and cloud resources to evaluate the performance of the BERT\, RoBERTa
 \, DistilBERT\, and XLNet models. We also discuss the design and prototypi
 ng of web applications to support the aided processing of representations 
 using Voilà\, FastAPI\, and React. Finally\, we highlight successes and c
 hallenges encountered and suggest areas for future improvement.
DTSTAMP:20260423T035124Z
LOCATION:A1
SUMMARY:Accelerating Public Consultations with Large Language Models: A Cas
 e Study from the UK Planning Inspectorate - Michele Dallachiesa\, Andreas 
 Leed
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/HMGCPL/
END:VEVENT
END:VCALENDAR