Modelpublic

bullmount/it_nerIta_trf

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

19likes22downloads

Model Card

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, WORKOFART, 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

<summary>View label scheme (18 labels)</summary>

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.
WORKOFART	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

</details>

Accuracy

Type	Score
`ENTS_F`	91.96
`ENTS_P`	91.47
`ENTS_R`	90.86