Zero-Shot Award Criteria extraction via Large Language Models from German Procurement Data from Switzerland

Matoshi, Veton; Rolshoven, Luca Sven; Stürmer, Matthias (10 June 2024). Zero-Shot Award Criteria extraction via Large Language Models from German Procurement Data from Switzerland In: 9th SwissText Swiss Text Analytics Conference 2024. Fachhochschule Graubünden (FHGR). 10.-11. Juni 2024.

Text Extracting_Award_Criteria-8.pdf Restricted to registered users only Download (2MB) | Request a copy

Public procurement serves as a model for sustainable practices (Sönnichsen and Clement, 2020). Recent legislation in Switzerland mandates considerations of economic, environmental, and social responsibility in public spending, including within the realm of public procurement. To assess the extent to which these legislative measures have influenced public procurement practices, one may examine Award Criteria (ACs) based on which procuring entities determine the most suitable bidder. This paper demonstrates the potential of Natural Language Processing (NLP) for extracting ACs from Swiss calls for tenders (CFTs), specifically those in German. We evaluate the efficacy of a German Large Language Model (LLM) in executing four tasks with a single zero-shot prompt: (1) Text Classification (TC), determining whether a call for tenders (CFT) includes ACs; (2) Named Entity Recognition (NER), identifying ACs and other related named entities; (3) Relation Extraction (RE), elucidating relationships between named entity instances; and (4) Formatting, compiling the information into a structured JSON format. We evaluate our approach on a set of 167 annotated CFTs. This approach facilitates the automated monitoring and evaluation of ACs overtime regarding sustainability. Both our code and the annotated dataset are publicly available: https://github.com/kapllan/GATE-CH.

Item Type:	Conference or Workshop Item (Paper)
Division/Institute:	Business School > Institute for Public Sector Transformation Business School
Name:	Matoshi, Veton0009-0002-6613-5701; Rolshoven, Luca Sven0009-0001-0663-9011 and Stürmer, Matthias0000-0001-9038-4041
Funders:	Organisations 10000100 not found.
Projects:	Projects 10000100 not found.
Language:	English
Submitter:	Veton Matoshi
Date Deposited:	27 Aug 2024 09:53
Last Modified:	27 Aug 2024 09:58
Related URLs:	https://www.swisstext.org/
Uncontrolled Keywords:	public procurement; NLP; award criteria, sustainability
ARBOR DOI:	10.24451/arbor.22266
URI:	https://arbor.bfh.ch/id/eprint/22266