Description
This model is imported from Hugging Face-models. This model is the fine-tuned version of “xlm-roberta-base” (a multilingual version of RoBERTa) using a reviewed version of well known Turkish NER dataset (https://github.com/stefan-it/turkish-bert/files/4558187/nerdata.txt)
Predicted Entities
PER, LOC, ORG
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
tokenClassifier = XlmRoBertaForTokenClassification.pretrained("xlm_roberta_base_token_classifier_ner", "tr"))\
.setInputCols(["sentence",'token'])\
.setOutputCol("ner")
ner_converter = NerConverter()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")
nlpPipeline = Pipeline(stages=[documentAssembler, sentenceDetector, tokenizer, tokenClassifier, ner_converter])
empty_data = spark.createDataFrame([[""]]).toDF("text")
model = nlpPipeline.fit(empty_data)
text = """Benim adım Cesur Yurttaş ve İstanbul'da yaşıyorum."""
result = model.transform(spark.createDataFrame([[text]]).toDF("text"))
val documentAssembler = DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")
.setInputCols(Array("document"))
.setOutputCol("sentence")
val tokenizer = Tokenizer()
.setInputCols(Array("sentence"))
.setOutputCol("token")
val tokenClassifier = XlmRoBertaForTokenClassification.pretrained("xlm_roberta_base_token_classifier_ner", "tr"))
.setInputCols(Array("sentence","token"))
.setOutputCol("ner")
ner_converter = NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
val pipeline = new Pipeline().setStages(Array(documentAssembler, sentenceDetector, tokenizer, tokenClassifier, ner_converter))
val example = Seq.empty["Benim adım Cesur Yurttaş ve İstanbul'da yaşıyorum."].toDS.toDF("text")
val result = pipeline.fit(example).transform(example)
import nlu
nlu.load("tr.ner.xlm_roberta").predict("""Benim adım Cesur Yurttaş ve İstanbul'da yaşıyorum.""")
Results
+-------------+---------+
|chunk |ner_label|
+-------------+---------+
|Cesur Yurttaş|PER |
|İstanbul'da |LOC |
+-------------+---------+
Model Information
| Model Name: | xlm_roberta_base_token_classifier_ner |
| Compatibility: | Spark NLP 3.3.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [ner] |
| Language: | tr |
| Case sensitive: | true |
| Max sentense length: | 256 |
Data Source
https://huggingface.co/akdeniz27/xlm-roberta-base-turkish-ner
Benchmarking
accuracy: 0.9919343118732742
f1: 0.9492100796448622
precision: 0.9407349896480332
recall: 0.9578392621870883