Conference item icon

Conference item

Improving language model predictions via prompts enriched with knowledge graphs

Abstract:
Despite advances in deep learning and knowledge graphs (KGs), using language models for natural language understanding and question answering remains a challenging task. Pre-trained language models (PLMs) have shown to be able to leverage contextual information, to complete cloze prompts, next sentence completion and question answering tasks in various domains. Unlike structured data querying in e.g. KGs, mapping an input question to data that may or may not be stored by the language model is not a simple task. Recent studies have highlighted the improvements that can be made to the quality of information retrieved from PLMs by adding auxiliary data to otherwise naive prompts. In this paper, we explore the effects of enriching prompts with additional contextual information leveraged from the Wikidata KG on language model performance. Specifically, we compare the performance of naive vs. KG-engineered cloze prompts for entity genre classification in the movie domain. Selecting a broad range of commonly available Wikidata properties, we show that enrichment of cloze-style prompts with Wikidata information can result in a significantly higher recall for the investigated BERT and RoBERTa large PLMs. However, it is also apparent that the optimum level of data enrichment differs between models.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publication website:
https://ceur-ws.org/Vol-3342/

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
St Hugh's College
Role:
Author
ORCID:
0000-0002-4486-1262


Publisher:
CEUR Workshop Proceedings
Host title:
Proceedings of the Workshop on Deep Learning for Knowledge Graphs (DL4KG 2022)
Article number:
3
Series:
CEUR Workshop Proceedings
Series number:
3342
Publication date:
2023-02-11
Acceptance date:
2022-09-29
Event title:
Workshop on Deep Learning for Knowledge Graphs (DL4KG@ISWC)
Event location:
Virtual event
Event website:
https://alammehwish.github.io/dl4kg2022/
Event start date:
2022-10-24
Event end date:
2022-10-24
ISSN:
1613-0073


Language:
English
Keywords:
Pubs id:
1328783
Local pid:
pubs:1328783
Deposit date:
2023-02-17

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP