Towards the Construction of a WordNet for Old English

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 3934–3941 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 3934 Towards the Construction of a WordNet for Old English Background, Methods, Infrastructure Anas Fahad Khan1, Francisco J. Minaya G´omez2, Rafael Cruz Gonz´alez2, Harry Diakoff3, Javier Diaz Vera2, John P. McCrae4, Ciara O’Loughlin4, William Michael Short5 Sander Stolk6 1Istituto di Linguistica Computazionale “A. Zampolli” (ILC-CNR) Pisa, Italy, 2University of Castilla-La Mancha, Ciudad Real, Spain, 3The Alpheios Project, 4Data Science Institute, National University of Ireland Galway, 5 University of Exeter, UK; 6Leiden University, Leiden, the Netherlands, 1fahad.khan@ilc.cnr.it, 2{francisco.minaya, rafael.cruz, javierenrique.diaz}@uclm.es 3harry.diakoff@gmail.com, 4john@mccr.ae, ciara.oloughlin@insight-centre.org, 5w.short@exeter.ac.uk, 6s.s.stolk@hum.leidenuniv.nl Abstract In this paper we will discuss our preliminary work towards the construction of a WordNet for Old English, taking our inspiration from other similar WN construction projects for ancient languages such as Ancient Greek, Latin and Sanskrit (on this overall endeavour, see now (Biagetti et al., 2021)). The Old English WordNet (OldEWN) will build upon this innovative work in a number of different ways which we articulate in the article, most importantly by treating figurative meaning as a ’first-class citizen’ in the structuring of the semantic system. From a more practical perspective we will describe our plan to utilize a pre-existing lexicographic resource and the naisc system to automatically compile a provisional version of the WordNet which will then be checked and enriched by experts in Old English. Keywords: WordNet, ancient, figurative, metaphor, metonymy, conceptual metaphor, embodiment 1. Introduction In this paper we describe the proposed construction of a WordNet (WN) for the Old English language, the Old English WordNet (OldEWN). This resource will be based on lemmas and definitions extracted from a legacy Old English dictionary; these will be used to compile a list of candidate synsets and the relations be- tween them using the Naisc linking system. Finally the candidate synsets will be subject a process of correction and enrichment by a team of expert annotators using a specially developed platform. We plan to publish the resulting resource, the OldEWN with an open license, both in the Global Wordnet LMF XML format1 and as Linked Open Data using the RDF vocabulary OntoLex- Lemon. As we discuss below, this work is inspired by a number of previous efforts at creating historical lan- guage WN’s, in particular in its strong focus on figura- tive language and semantic shift. The rest of the article is structured as follows. We be- gin in Section 2.1 by giving some background on the Old English language itself and listing some of the lan- guage resources that currently exist for it. Next, in Sec- tion 2.3, we situate our proposals for a OldEWN in the context of other efforts in the construction of historic language WNs. Then in Section 3 we discuss the steps by which the OldEWN will be created using the Naisc system. Afterwards, in Section 4.1, we look at some sample entries from our proposed OldEWN using an enriched version …

Content truncated to 500 words