This study aims at using Named Entity Recognition (NER) to extract a specific type of multi-word entity, that is, multi-word organization names (MWORGs), from an English-Spanish comparable corpus of European Parliament documents. Following a triadic, Peircean model of translation and grammar, we hypothesize that MWORGs are nominal constructions (or signs) which serve a semiotic function of mediation in EU translations (Stecconi 2009;Torres-Martínez 2022). Specific performance of the VIP-DeepPavlov NER system (Corpas Pastor 2021) with MWORGs is evaluated in terms of precision, recall, and F-1 scores. Relevant MWORGs are then annotated and analyzed from a contrastive, semi-constructional approach (Boas 2010) to determine how many of them are mediating, and under which schemata. Results predictably show that non-mediating constructions are prevalent in non-translated English (66 %), as mediating constructions are in translated Spanish (81 %). However, a surprising 34 % of the organization names in non-translated English are mediating; inversely, 19 % of the MWORGs in translated Spanish serve a non-mediating function. Seven different mediation schemes (blending, borrowing, translation, and further combinations of the three) where discovered among MWORGs, some of them languagepreferent. This reinforces our belief that names are largely disregarded semiotic hubs, and indeed a crucial piece in the understanding of (non-)translations and (non-)interpretations as construction-based grammars with a specific number of similar, different, and mediating rules in each language and textual typology.

Construction Grammar (Hoffmann & Trousdale 2013) has received very little attention in onomastics, let alone corpus-based approaches, as corpora are just starting to be applied to the empirical study of names (Motschenbacher 2020). This study employs Named Entity Recognition plus verbal pattern extraction in an intermodal corpus (Bernardini 2016) of EU discourse, or Eurolect (Sandrelli 2018). The methodological aim is to mine English argument-structure constructions (Goldberg 1995) with subordinate clauses introduced by that and organization names in the subject slot ([ORG + V + that + SC]). First, the personification recognition method of Dorst, Mulder, and Steen (2011) is applied to quantitatively prove the strong relationship between the extracted argument-structure constructions and personification metaphors in EU discourse. Second, the constructions and their form-meaning pairings are described, both per subcorpus and globally. Results show that, at a macro- and meso-level of schematicity, the [ORG + V + that + SC] construction transversally symbolizes personification as an understanding scheme for institutional relations, constructing organization names with semantically human verbs of belief, speech, and thought. At a microscopic level, however, some constructions occur exclusively in one of the four subcorpora (non-translated, translated, non-interpreted, and interpreted English), meaning that they could be covering specific mediating functions through their name-verb slot choices.

No abstract

Reseña del libro de Lorena Arce y Miriam Seghiri "La traducción de contratos de compraventa inmobiliaria: un estudio basado en corpus aplicado a España e Irlanda", editado por Peter Lang.