%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Ro Core News Sm
CPU-optimized Romanian natural language processing model, including tokenization, part-of-speech tagging, dependency parsing, named entity recognition, and other functions
Downloads 17
Release Time : 3/2/2022
Model Overview
This is a small Romanian processing pipeline provided by spaCy, containing complete NLP components, suitable for basic analysis tasks of Romanian text.
Model Features
CPU Optimization
Specially optimized for CPU usage scenarios, suitable for resource-constrained environments
Complete NLP Pipeline
Includes a complete processing pipeline from tokenization to named entity recognition
High-Accuracy Part-of-Speech Tagging
Part-of-speech tagging accuracy reaches 95.58%
Multitask Learning
A single model handles multiple NLP tasks simultaneously
Model Capabilities
Tokenization
Part-of-speech Tagging
Dependency Parsing
Named Entity Recognition
Lemmatization
Sentence Segmentation
Use Cases
Text Analysis
Romanian Text Processing
Basic NLP processing of Romanian text
Obtain linguistic information such as tokenization, part-of-speech tagging, and dependency relations
Information Extraction
Named Entity Recognition
Identify entities such as person names, place names, and organization names from Romanian text
F1 score reaches 71.34%
๐ ro_core_news_sm
This is a Romanian language processing pipeline optimized for CPU, which can perform multiple token - classification tasks such as NER, TAG, POS, etc.
๐ Documentation
Details: https://spacy.io/models/ro#ro_core_news_sm
This is a Romanian pipeline optimized for CPU. Components: tok2vec, tagger, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.
| Property | Details |
|---|---|
| Name | ro_core_news_sm |
| Version | 3.7.0 |
| spaCy | >=3.7.0,<3.8.0 |
| Default Pipeline | tok2vec, tagger, parser, lemmatizer, attribute_ruler, ner |
| Components | tok2vec, tagger, parser, lemmatizer, senter, attribute_ruler, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | UD Romanian RRT v2.8 (Barbu Mititelu, Verginica; Irimia, Elena; Perez, Cenel - Augusto; Ion, Radu; Simionescu, Radu; Popel, Martin) RONEC - the Romanian Named Entity Corpus (ca9ce460) (Dumitrescu, Stefan Daniel; Avram, Andrei - Marius; Morogan, Luciana; Toma; Stefan) |
| License | CC BY - SA 4.0 |
| Author | Explosion |
Label Scheme
View label scheme (540 labels for 3 components)
| Component | Labels |
|---|---|
tagger |
ARROW, Af, Afcfp-n, Afcfson, Afcfsrn, Afcmpoy, Afcms-n, Afp, Afp-p-n, Afp-poy, Afp-srn, Afpf--n, Afpfp-n, Afpfp-ny, Afpfpoy, Afpfpry, Afpfson, Afpfsoy, Afpfsrn, Afpfsry, Afpm--n, Afpmp-n, Afpmpoy, Afpmpry, Afpms-n, Afpmsoy, Afpmsry, Afsfp-n, Afsfsrn, BULLET, COLON, COMMA, Ccssp, Ccsspy, Crssp, Csssp, Cssspy, DASH, DBLQ, Dd3-po---e, Dd3-po---o, Dd3fpo, Dd3fpr, Dd3fpr---e, Dd3fpr---o, Dd3fpr--y, Dd3fso, Dd3fso---e, Dd3fsr, Dd3fsr---e, Dd3fsr---o, Dd3fsr--yo, Dd3mpo, Dd3mpr, Dd3mpr---e, Dd3mpr---o, Dd3mso---e, Dd3msr, Dd3msr---e, Dd3msr---o, Dh1ms, Dh3fp, Dh3fso, Dh3fsr, Dh3mp, Dh3ms, Di3, Di3-----y, Di3--r---e, Di3-po, Di3-po---e, Di3-sr, Di3-sr---e, Di3-sr--y, Di3fp, Di3fpr, Di3fpr---e, Di3fso, Di3fso---e, Di3fsr, Di3fsr---e, Di3mp, Di3mpr, Di3mpr---e, Di3ms, Di3ms----e, Di3mso---e, Di3msr, Di3msr---e, Ds1fp-p, Ds1fp-s, Ds1fsop, Ds1fsos, Ds1fsrp, Ds1fsrs, Ds1fsrs-y, Ds1mp-p, Ds1mp-s, Ds1ms-p, Ds1ms-s, Ds1msrs-y, Ds2---s, Ds2fp-p, Ds2fp-s, Ds2fsrp, Ds2fsrs, Ds2mp-p, Ds2mp-s, Ds2ms-p, Ds2ms-s, Ds3---p, Ds3---s, Ds3---sy, Ds3fp-s, Ds3fsos, Ds3fsrs, Ds3mp-s, Ds3ms-s, Dw3--r---e, Dw3-po---e, Dw3fpr, Dw3fso---e, Dw3fsr, Dw3mpr, Dw3mso---e, Dw3msr, Dz3fsr---e, Dz3mso---e, Dz3msr---e, EQUAL, EXCL, EXCLHELLIP, GE, GT, HELLIP, I, LCURL, LPAR, LSQR, LT, M, Mc-p-d, Mc-p-l, Mc-s-b, Mc-s-d, Mc-s-l, Mcfp-l, Mcfp-ln, Mcfprln, Mcfprly, Mcfsoln, Mcfsrl, Mcfsrln, Mcfsrly, Mcmp-l, Mcms-ln, Mcmsrl, Mcmsrln, Mcmsrly, Mffprln, Mffsrln, Mlfpo, Mlfpr, Mlmpr, Mo---l, Mo---ln, Mo-s-r, Mofp-ln, Mofpoly, Mofprly, Mofs-l, Mofsoln, Mofsoly, Mofsrln, Mofsrly, Mompoly, Momprly, Moms-l, Moms-ln, Momsoly, Momsrly, Nc, Nc---n, Ncf--n, Ncfp-n, Ncfpoy, Ncfpry, Ncfs-n, Ncfson, Ncfsoy, Ncfsrn, Ncfsry, Ncfsryy, Ncfsvy, Ncm--n, Ncmp-n, Ncmpoy, Ncmpry, Ncms-n, Ncms-ny, Ncms-y, Ncmsoy, Ncmsrn, Ncmsry, Ncmsryy, Ncmsvn, Ncmsvy, Np, Npfson, Npfsoy, Npfsrn, Npfsry, Npmpoy, Npmpry, Npms-n, Npmsoy, Npmsry, PERCENT, PERIOD, PLUS, PLUSMINUS, Pd3-po, Pd3fpr, Pd3fso, Pd3fsr, Pd3mpo, Pd3mpr, Pd3mpr--y, Pd3mso, Pd3msr, Pi3--r, Pi3-po, Pi3-so, Pi3-sr, Pi3fpr, Pi3fso, Pi3fsr, Pi3mpr, Pi3mso, Pi3msr, Pi3msr--y, Pp1-pa--------w, Pp1-pa--y-----w, Pp1-pd--------s, Pp1-pd--------w, Pp1-pd--y-----w, Pp1-pr--------s, Pp1-sa--------s, Pp1-sa--------w, Pp1-sa--y-----w, Pp1-sd--------s, Pp1-sd--------w, Pp1-sd--y-----w, Pp1-sn--------s, Pp2-----------s, Pp2-pa--------w, Pp2-pa--y-----w, Pp2-pd--------w, Pp2-pd--y-----w, Pp2-pr--------s, Pp2-sa--------s, Pp2-sa--------w, Pp2-sa--y-----w, Pp2-sd--------s, Pp2-sd--------w, Pp2-sd--y-----w, Pp2-sn--------s, Pp2-so--------s, Pp2-sr--------s, Pp3-p---------s, Pp3-pd--------w, Pp3-pd--y-----w, Pp3-po--------s, Pp3-sd--------w, Pp3-sd--y-----w, Pp3-so--------s, Pp3fpa--------w, Pp3fpa--y-----w, Pp3fpr--------s, Pp3fs---------s, Pp3fsa--------w, Pp3fsa--y-----w, Pp3fso--------s, Pp3fsr--------s, Pp3fsr--y-----s, Pp3mpa--------w, Pp3mpa--y-----w, Pp3mpr--------s, Pp3ms---------s, Pp3msa--------w, Pp3msa--y-----w, Pp3mso--------s, Pp3msr--------s, Pp3msr--y-----s, Ps1fp-s, Ps1fsrp, Ps1fsrs, Ps1mp-p, Ps1ms-p, Ps2fp-s, Ps2fsrp, Ps2fsrs, Ps3---p, Ps3---s, Ps3fp-s, Ps3fsrs, Ps3mp-s, Ps3ms-s, Pw3--r, Pw3-po, Pw3-so, Pw3fpr, Pw3fso, Pw3mpr, Pw3mso, Px3--a--------s, Px3--a--------w, Px3--a--y-----w, Px3--d--------w, Px3--d--y-----w, Pz3-sr, Pz3fsr, QUEST, QUOT, Qf, Qn, Qs, Qs-y, Qz, Qz-y, RCURL, RPAR, RSQR, Rc, Rgp, Rgpy, Rgs, Rp, Rw, Rw-y, Rz, SCOLON, SLASH, STAR, Sp, Spsa, Spsay, Spsd, Spsg, Td-po, Tdfpr, Tdfso, Tdfsr, Tdmpr, Tdmso, Tdmsr, Tf-so, Tffpoy, Tffpry, Tffs-y, Tfmpoy, Tfms-y, Tfmsoy, Tfmsry, Ti-po, Tifp-y, Tifso, Tifsr, Timso, Timsr, Tsfp, Tsfs, Tsmp, Tsms, UNDERSC, Va--1, Va--1-----y, Va--1p, Va--1s, Va--1s----y, Va--2p, Va--2p----y, Va--2s, Va--2s----y, Va--3, Va--3-----y, Va--3p, Va--3p----y, Va--3s, Va--3s----y, Vag, Vag-------y, Vaii1, Vaii2s, Vaii3p, Vaii3s, Vail3p, Vail3s, Vaip1p, Vaip1s, Vaip2p, Vaip2s, Vaip3p, Vaip3p----y, Vaip3s, Vaip3s----y, Vais3p, Vais3s, Vam-2s, Vanp, Vap--sm, Vasp1p, Vasp1s, Vasp2p, Vasp2s, Vasp3, Vmg, Vmg-------y, Vmii1, Vmii1-----y, Vmii2p, Vmii2s, Vmii3p, Vmii3p----y, Vmii3s, Vmii3s----y, Vmil1, Vmil1p, Vmil2s, Vmil3p, Vmil3p----y, Vmil3s, Vmil3s----y, Vmip1p, Vmip1p----y, Vmip1s, Vmip1s----y, Vmip2p, Vmip2s, Vmip2s----y, Vmip3, Vmip3-----y, Vmip3p, Vmip3s, Vmip3s----y, Vmis1p, Vmis1s, Vmis3p, Vmis3p----y, Vmis3s, Vmis3s----y, Vmm-2p, Vmm-2s, Vmnp, Vmnp------y, Vmp--pf, Vmp--sf, Vmp--sm, Vmp--sm---y, Vmsp1p, Vmsp2p, Vmsp2s, Vmsp3, Vmsp3-----y, X, Y, Ya, Yn, Ynfsoy, Ynfsry, Ynmsoy, Ynmsry, Yp, Yp,Yn, Yp-sr, Yr, _SP |
parser |
ROOT, acl, advcl, advcl:tcl, advmod, advmod:tmod, amod, appos, aux, aux:pass, case, cc, cc:preconj, ccomp, ccomp:pmod, compound, conj, cop, csubj, csubj:pass, dep, det, expl, expl:impers, expl:pass, expl:poss, expl:pv, fixed, flat, goeswith, iobj, mark, nmod, nmod:tmod, nsubj, nsubj:pass, nummod, obj, obl, obl:agent, obl:pmod, orphan, parataxis, punct, vocative, xcomp |
ner |
DATETIME, EVENT, FACILITY, GPE, LANGUAGE, LOC, MONEY, NAT_REL_POL, NUMERIC_VALUE, ORDINAL, ORGANIZATION, PERIOD, PERSON, PRODUCT, QUANTITY, WORK_OF_ART |
Accuracy
| Type | Score |
|---|---|
TOKEN_ACC |
99.80 |
TOKEN_P |
99.67 |
TOKEN_R |
99.57 |
TOKEN_F |
99.59 |
TAG_ACC |
95.58 |
SENTS_P |
96.01 |
SENTS_R |
96.01 |
SENTS_F |
96.01 |
DEP_UAS |
87.15 |
DEP_LAS |
81.29 |
LEMMA_ACC |
95.05 |
POS_ACC |
92.83 |
MORPH_ACC |
94.05 |
MORPH_MICRO_P |
98.20 |
MORPH_MICRO_R |
95.20 |
MORPH_MICRO_F |
96.43 |
ENTS_P |
72.33 |
ENTS_R |
70.38 |
ENTS_F |
71.34 |
๐ง Technical Details
Model Performance Metrics
The ro_core_news_sm model has been evaluated on multiple token - classification tasks, and here are the detailed metrics:
| Task | Metric | Value |
|---|---|---|
| NER | NER Precision | 0.7232530596 |
| NER | NER Recall | 0.7038033039 |
| NER | NER F Score | 0.7133956386 |
| TAG | TAG (XPOS) Accuracy | 0.9557849059 |
| POS | POS (UPOS) Accuracy | 0.9282856599 |
| MORPH | Morph (UFeats) Accuracy | 0.9405383217 |
| LEMMA | Lemma Accuracy | 0.9504793737 |
| UNLABELED_DEPENDENCIES | Unlabeled Attachment Score (UAS) | 0.8715455315 |
| LABELED_DEPENDENCIES | Labeled Attachment Score (LAS) | 0.812886226 |
| SENTS | Sentences F - Score | 0.960106383 |
๐ License
This project is licensed under the CC BY - SA 4.0 license.
Indonesian Roberta Base Posp Tagger
MIT
This is a POS tagging model fine-tuned based on the Indonesian RoBERTa model, trained on the indonlu dataset for Indonesian text POS tagging tasks.
Sequence Labeling
Transformers Other
Transformers OtherI
w11wo
2.2M
7
Bert Base NER
MIT
BERT fine-tuned named entity recognition model capable of identifying four entity types: Location (LOC), Organization (ORG), Person (PER), and Miscellaneous (MISC)
Sequence Labeling English
B
dslim
1.8M
592
Deid Roberta I2b2
MIT
This model is a sequence labeling model fine-tuned on RoBERTa, designed to identify and remove Protected Health Information (PHI/PII) from medical records.
Sequence Labeling Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesD
obi
1.1M
33
Ner English Fast
Flair's built-in fast English 4-class named entity recognition model, based on Flair embeddings and LSTM-CRF architecture, achieving an F1 score of 92.92 on the CoNLL-03 dataset.
Sequence Labeling
PyTorch English
PyTorch EnglishN
flair
978.01k
24
French Camembert Postag Model
French POS tagging model based on Camembert-base, trained using the free-french-treebank dataset
Sequence Labeling Transformers French
Transformers FrenchF
gilf
950.03k
9
Xlm Roberta Large Ner Spanish
A Spanish named entity recognition model fine-tuned based on the XLM-Roberta-large architecture, with excellent performance on the CoNLL-2002 dataset.
Sequence Labeling Transformers Spanish
Transformers SpanishX
MMG
767.35k
29
Nusabert Ner V1.3
MIT
Named entity recognition model fine-tuned on Indonesian NER tasks based on NusaBert-v1.3
Sequence Labeling Transformers Other
Transformers OtherN
cahya
759.09k
3
Ner English Large
Flair framework's built-in large English NER model for 4 entity types, utilizing document-level XLM-R embeddings and FLERT technique, achieving an F1 score of 94.36 on the CoNLL-03 dataset.
Sequence Labeling PyTorch English
PyTorch EnglishN
flair
749.04k
44
Punctuate All
MIT
A multilingual punctuation prediction model fine-tuned based on xlm-roberta-base, supporting automatic punctuation completion for 12 European languages
Sequence Labeling Transformers
TransformersP
kredor
728.70k
20
Xlm Roberta Ner Japanese
MIT
Japanese named entity recognition model fine-tuned based on xlm-roberta-base
Sequence Labeling Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesX
tsmatz
630.71k
25
Featured Recommended AI Models
ยฉ 2025AIbase