This article presents a set of standardised corpora of poetry comprising over 330,000 poems in ten languages (Czech, English, French, German, Hungarian, Italian, Portuguese, Russian, Slovenian, and Spanish). Each corpus has been deduplicated, enriched with Universal Dependencies, provided with additional metadata, and converted into a unified json structure.
Named entity recognition (NER) and named entity linking (NEL) remain underexplored in poetic texts. This study provides the first large-scale evaluation of contemporary NER and NEL systems on poetry across seven European languages – Czech, German, English, French, Italian, Russian, and Slovenian – using corpora from the PoeTree project. We benchmark three NER systems (flair, NameTag 2, spaCy) and three GPT models (GPT-3.5, GPT-4, GPT-4 Turbo) against manually annotated gold standards. While results fall short of in-domain benchmarks, they significantly outperform earlier findings. Manual correction further raises final annotation quality to estimated F1 scores between 0.77 and 0.93 across languages. We additionally evaluate two NEL systems – spaCy fishing and mGenre – showing that mGenre consistently outperforms spaCy fishing, achieving in-KB F1-scores of 0.70–0.81. By analysing geographic distances between predicted and gold-standard links, we demonstrate that a substantial portion of “incorrect” predictions are near-miss ambiguities rather than substantive errors. The resulting manually verified geolocation annotations have been integrated into PoeTree and made available through an interactive map interface.
Eden osrednjih pojmov, ko razmišljamo o tem, kaj pomeni razumeti jezik, literaturo, kulturo ter zakaj nam zgolj poznavanje besed in stavčnih vzorcev v drugačnih družbenih ali kulturnih okoljih ne omogoča vedno interpretirati povedanega ali izraziti svojih misli, je podoba, ki je postavljena v središče znanstvenega razmisleka ob 60. seminarju slovenskega jezika, literature in kulture. Podoba je namreč pojem, v katerem se prepletajo trije gradniki sporočila: izraz oziroma posebna raba jezika; preneseni in konotativni pomeni, ki se temu izrazu pripisujejo; in kontekstualni okvir, v katerem z danim izrazom izbrani pomen upovedujemo in mu dajemo smisel.
This paper explores the nature of Slavic spoken verse, delving into the questions of reconstruction and derivation from a common Slavic verse. It also investigates the development of the said form, using Slovenian weather proverbs as a case study. The study analyzes proverbs from a verse study perspective rather than a folkloristic or linguistic one. Thus, it emphasizes the importance of including forms like proverbs in the field of verse study.
Prispevek izpostavlja izbrane verzološke termine, ki znotraj slovenske verzološke stroke izkazujejo določeno mero neustaljenosti. Na kratko so predstavljeni tudi začetki slovenske verzološke terminologije. Terminološka poimenovanja za temeljne verzološke pojme, začenši z imenom discipline, so osvetljena etimološko, ob čemer so vzporejana z ustreznimi tujejezičnimi poimenovanji. Izpostavljenih je tudi nekaj terminov, ki jih je skoval najuglednejši slovenski verzolog Boris A. Novak. Na podlagi izbranih primerov prispevek poudarja nujnost obstoja ustreznega terminološkega aparata za vitalnost posameznega strokovnega področja.