Model description (NerIta)
it_nerIta_trf is a fine-tuned spacy model ready to be used for Named Entity Recognition on Italian language texts based on a pipeline composed by the hseBert-it-cased transformer.
It has been trained to recognize 18 types of entities: PER, NORP, ORG, GPE, LOC, DATE, MONEY, FAC, PRODUCT, EVENT, WORK_OF_ART, LAW, LANGUAGE, TIME, PERCENT, QUANTITY, ORDINAL, CARDINAL. See table below for details.
| Feature |
Description |
| Name |
nerIta_trf |
| Version |
0.0.1 |
| spaCy |
>=3.2.1,<3.3.0 |
| Default Pipeline |
transformer, ner |
| Components |
transformer, ner |
| Based on transformer |
bullmount/hseBert-it-cased |
| Sources |
n/a |
| License |
n/a |
| Author |
n/a |
Label Scheme
View label scheme (18 labels)
Predicts 18 tags:
| tag |
meaning |
| PER |
People, including fictional. |
| NORP |
Nationalities or religious or political groups. |
| ORG |
Companies, agencies, institutions, etc. |
| GPE |
Countries, cities, states. |
| LOC |
Non-GPE locations, mountain ranges, bodies of water. |
| DATE |
Absolute or relative dates or periods. |
| MONEY |
Monetary values, including unit. |
| FAC |
Buildings, airports, highways, bridges, etc. |
| PRODUCT |
Objects, vehicles, foods, etc. (Not services.) |
| EVENT |
Named hurricanes, battles, wars, sports events, etc. |
| WORK_OF_ART |
Titles of books, songs, etc. |
| LAW |
Named documents made into laws. |
| LANGUAGE |
Any named language. |
| TIME |
Times smaller than a day. |
| PERCENT |
Percentage, including "%". |
| QUANTITY |
Measurements, as of weight or distance. |
| ORDINAL |
"first", "second", etc. |
| CARDINAL |
Numerals that do not fall under another type. |
| MISC |
other name |
Accuracy
| Type |
Score |
ENTS_F |
91.96 |
ENTS_P |
91.47 |
ENTS_R |
90.86 |
