Prompting as Probing: Using Language Models for Knowledge Base Construction

Dimitrios Alivanistos, Selene Báez Santamaría, Michael Cochez, Jan Christoph Kalo, Emile van Krieken, Thiviyan Thanapalasingam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Language Models (LMs) have proven to be useful in various downstream applications, such as sum-marisation, translation, question answering and text classification. LMs are becoming increasingly important tools in Artificial Intelligence, because of the vast quantity of information they can store. In this work, we present ProP (Prompting as Probing), which utilizes GPT-3, a large Language Model originally proposed by OpenAI in 2020, to perform the task of Knowledge Base Construction (KBC). ProP implements a multi-step approach that combines a variety of prompting techniques to achieve this. Our results show that manual prompt curation is essential, that the LM must be encouraged to give answer sets of variable lengths, in particular including empty answer sets, that true/false questions are a useful device to increase precision on suggestions generated by the LM, that the size of the LM is a crucial factor, and that a dictionary of entity aliases improves the LM score. Our evaluation study indicates that these proposed techniques can substantially enhance the quality of the final predictions: ProP won track 2 of the LM-KBC competition, outperforming the baseline by 36.4 percentage points. Our implementation is available on https://github.com/HEmile/iswc-challenge.
Original languageEnglish
Title of host publicationLM-KBC 2022 Knowledge Base Construction from Pre-trained Language Models 2022
Subtitle of host publicationProceedings of the Semantic Web Challenge on Knowledge Base Construction from Pre-trained Language Models 2022 co-located with the 21st International Semantic Web Conference (ISWC2022)
EditorsSneha Singhania, Tuan-Phong Nguyen, Simon Razniewski
PublisherCEUR-WS.org
Pages11-34
Number of pages24
Volume3274
Publication statusPublished - 16 Nov 2022
EventKnowledge Base Construction from Pre-trained Language Models 2022 - Virtual event
Duration: 1 Oct 2022 → …

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR-WS.org
ISSN (Electronic)1613-0073

Workshop

WorkshopKnowledge Base Construction from Pre-trained Language Models 2022
Abbreviated titleLM-KBC 2022
Period1/10/22 → …

Fingerprint

Dive into the research topics of 'Prompting as Probing: Using Language Models for Knowledge Base Construction'. Together they form a unique fingerprint.

Cite this