Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models

Zdeněk Kasner, Ioannis Konstas, Ondřej Dušek

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

2 Citations (Scopus)

Abstract

Pretrained language models (PLMs) for data-to-text (D2T) generation can use human-readable data labels such as column headings, keys, or relation names to generalize to out-of-domain examples. However, the models are well-known in producing semantically inaccurate outputs if these labels are ambiguous or incomplete, which is often the case in D2T datasets. In this paper, we expose this issue on the task of descibing a relation between two entities. For our experiments, we collect a novel dataset for verbalizing a diverse set of 1,522 unique relations from three large-scale knowledge graphs (Wikidata, DBPedia, YAGO). We find that although PLMs for D2T generation expectedly fail on unclear cases, models trained with a large variety of relation labels are surprisingly robust in verbalizing novel, unseen relations. We argue that using data with a diverse set of clear and meaningful labels is key to training D2T generation systems capable of generalizing to novel domains.

Original languageEnglish
Title of host publication17th Conference of the European Chapter of the Association for Computational Linguistics
PublisherAssociation for Computational Linguistics
Pages2390-2407
Number of pages18
ISBN (Electronic)9781959429449
Publication statusPublished - 2023
Event17th Conference of the European Chapter of the Association for Computational Linguistics 2023 - Dubrovnik, Croatia
Duration: 2 May 20236 May 2023

Conference

Conference17th Conference of the European Chapter of the Association for Computational Linguistics 2023
Abbreviated titleEACL 2023
Country/TerritoryCroatia
CityDubrovnik
Period2/05/236/05/23

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models'. Together they form a unique fingerprint.

Cite this