Entity Linking (EL) systems have achieved impressive results on standard benchmarks, mainly thanks to the contextualized representations provided by recent pretrained language models. However, such systems still require massive amounts of data — millions of labeled examples — to perform at their best, with training times that often exceed several days, especially when limited computational resources are available. In this paper, we look at how Named Entity Recognition (NER) can be exploited to narrow the gap between EL systems trained on high and low amounts of labeled data. More specifically, we show how and to what extent an EL system can benefit from NER to enhance its entity representations, improve candidate selection, select more effective negative samples and enforce hard and soft constraints on its output entities. We release our software — code and model checkpoints — at https://github.com/Babelscape/ner4el

Named entity recognition for entity linking: what works and what’s next / Tedeschi, Simone; Conia, Simone; Cecconi, Francesco; Navigli, Roberto. - (2021), pp. 2584-2596. ((Intervento presentato al convegno Empirical Methods in Natural Language Processing tenutosi a Punta Cana, Dominican Republic [10.18653/v1/2021.findings-emnlp.220].

Named entity recognition for entity linking: what works and what’s next

Tedeschi, Simone
Primo
;
Conia, Simone
Secondo
;
Cecconi, Francesco
Penultimo
;
Navigli, Roberto
Ultimo
2021

Abstract

Entity Linking (EL) systems have achieved impressive results on standard benchmarks, mainly thanks to the contextualized representations provided by recent pretrained language models. However, such systems still require massive amounts of data — millions of labeled examples — to perform at their best, with training times that often exceed several days, especially when limited computational resources are available. In this paper, we look at how Named Entity Recognition (NER) can be exploited to narrow the gap between EL systems trained on high and low amounts of labeled data. More specifically, we show how and to what extent an EL system can benefit from NER to enhance its entity representations, improve candidate selection, select more effective negative samples and enforce hard and soft constraints on its output entities. We release our software — code and model checkpoints — at https://github.com/Babelscape/ner4el
File allegati a questo prodotto
File Dimensione Formato  
Tedeschi_Named:2021.pdf

accesso aperto

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Creative commons
Dimensione 772.68 kB
Formato Adobe PDF
772.68 kB Adobe PDF Visualizza/Apri 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/11573/1599786
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact