| Title: | Named entity recognition and linking in PoeTree corpora |
|---|
| Authors: | ID Plecháč, Petr (Author)
ID Šeļa, Artjoms (Author)
ID Cinková, Silvie (Author)
ID De Sisto, Mirella (Author)
ID Nugues, Lara (Author)
ID Kočnik, Neža (Author)
ID Kolár, Robert (Author)
ID Haider, Thomas (Author) |
|---|
| Files: |  RAZ_Plecháč_Petr_2025.pdf (508,20 KB)
MD5: 6BE729514C66DD67EBA6022F12997958
 https://ojs.utlib.ee/index.php/smp/article/view/26645/20196
|
|---|
| Language: | English |
|---|
| Work type: | Scientific work |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FF - Faculty of Arts
|
|---|
| Abstract: | 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. |
|---|
| Keywords: | poetry, named entities, computational poetics, natural language processing |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Publication date: | 31.12.2025 |
|---|
| Place of publishing: | Tartu |
|---|
| Publisher: | University of Tartu Press |
|---|
| Year of publishing: | 2025 |
|---|
| Number of pages: | str. 7-18 |
|---|
| Numbering: | Letn. 12, št. 2 |
|---|
| PID: | 20.500.12556/DKUM-98082  |
|---|
| UDC: | 82 |
|---|
| ISSN on article: | 2346-691X |
|---|
| COBISS.SI-ID: | 277968387 |
|---|
| DOI: | 10.12697/smp.2025.12.2.01 |
|---|
| Publication date in DKUM: | 19.05.2026 |
|---|
| Views: | 118 |
|---|
| Downloads: | 1 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
