Recent work in Natural Language Processing and Computer Vision has been using textual information – e.g., entity names and descriptions – available in knowledge graphs to ground neural models to high-quality structured data. However, when it comes to non-English languages, the quantity and quality of textual information are comparatively scarce. To address this issue, we introduce the novel task of automatic Knowledge Graph Completion (KGE) and perform a thorough investigation on bridging the gap in both the quantity and quality of textual information between English and non-English languages. More specifically, we: i) bring to light the problem of increasing multilingual coverage and precision of entity names and descriptions in Wikidata; ii) demonstrate that state-of-the-art methods, namely, Machine Translation (MT), Web Search (WS), and Large Language Models (LLMs), struggle with this task; iii) present M-NTA, a novel unsupervised approach that combines MT, WS, and LLMs to generate high-quality textual information; and, iv) study the impact of increasing multilingual coverage and precision of non-English textual information in Entity Linking, Knowledge Graph Completion, and Question Answering. As part of our effort towards better multilingual knowledge graphs, we also introduce WikiKGE-10, the first human-curated benchmark to evaluate KGE approaches in 10 languages across 7 language families.

Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs / Conia, Simone; Li, Min; Lee, Daniel; Farooq Minhas, Umar; Ilyas, Ihab; Li, Yunyao. - (2023), pp. 1612-1634. (Intervento presentato al convegno Empirical Methods in Natural Language Processing tenutosi a Singapore) [10.18653/v1/2023.emnlp-main.100].

Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs

Simone Conia
Primo
;
2023

Abstract

Recent work in Natural Language Processing and Computer Vision has been using textual information – e.g., entity names and descriptions – available in knowledge graphs to ground neural models to high-quality structured data. However, when it comes to non-English languages, the quantity and quality of textual information are comparatively scarce. To address this issue, we introduce the novel task of automatic Knowledge Graph Completion (KGE) and perform a thorough investigation on bridging the gap in both the quantity and quality of textual information between English and non-English languages. More specifically, we: i) bring to light the problem of increasing multilingual coverage and precision of entity names and descriptions in Wikidata; ii) demonstrate that state-of-the-art methods, namely, Machine Translation (MT), Web Search (WS), and Large Language Models (LLMs), struggle with this task; iii) present M-NTA, a novel unsupervised approach that combines MT, WS, and LLMs to generate high-quality textual information; and, iv) study the impact of increasing multilingual coverage and precision of non-English textual information in Entity Linking, Knowledge Graph Completion, and Question Answering. As part of our effort towards better multilingual knowledge graphs, we also introduce WikiKGE-10, the first human-curated benchmark to evaluate KGE approaches in 10 languages across 7 language families.
2023
Empirical Methods in Natural Language Processing
knowledge graphs; multilingual; natural language processing; large language models; machine translation
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs / Conia, Simone; Li, Min; Lee, Daniel; Farooq Minhas, Umar; Ilyas, Ihab; Li, Yunyao. - (2023), pp. 1612-1634. (Intervento presentato al convegno Empirical Methods in Natural Language Processing tenutosi a Singapore) [10.18653/v1/2023.emnlp-main.100].
File allegati a questo prodotto
File Dimensione Formato  
Conia_Increasing_2023.pdf

accesso aperto

Note: https://aclanthology.org/2023.emnlp-main.100.pdf
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.59 MB
Formato Adobe PDF
4.59 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1696397
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact