Description
A Part of Speech classifier predicts a grammatical label for every token in the input text. Implemented with an averaged perceptron architecture.
Predicted Entities
- ADJ
- ADP
- ADV
- AUX
- CCONJ
- DET
- NOUN
- NUM
- PART
- PRON
- PROPN
- PUNCT
- VERB
- X
Live Demo Open in Colab Download Copy S3 URI
How to use
document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentence_detector = SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols("sentence")\
.setOutputCol("token")
pos = PerceptronModel.pretrained("pos_snk", "sk")\
.setInputCols(["document", "token"])\
.setOutputCol("pos")
pipeline = Pipeline(stages=[
document_assembler,
sentence_detector,
tokenizer,
posTagger
])
example = spark.createDataFrame([['Potom Maju nežne pohladila po hlávke a vraví : Spoznáš krásny veľký svet , Maja , hrejivé slniečko a nádherné lúky plné kvetov .']], ["text"])
result = pipeline.fit(example).transform(example)
val document_assembler = DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentence_detector = SentenceDetector()
.setInputCols("document")
.setOutputCol("sentence")
val tokenizer = Tokenizer()
.setInputCols("sentence")
.setOutputCol("token")
val pos = PerceptronModel.pretrained("pos_snk", "sk")
.setInputCols(Array("document", "token"))
.setOutputCol("pos")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector,, pos))
val data = Seq("Potom Maju nežne pohladila po hlávke a vraví : Spoznáš krásny veľký svet , Maja , hrejivé slniečko a nádherné lúky plné kvetov .").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
text = [""Potom Maju nežne pohladila po hlávke a vraví : Spoznáš krásny veľký svet , Maja , hrejivé slniečko a nádherné lúky plné kvetov .""]
token_df = nlu.load('sk.pos.snk').predict(text)
token_df
Results
+--------------------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+
|text |result |
+--------------------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+
|Potom Maju nežne pohladila po hlávke a vraví : Spoznáš krásny veľký svet , Maja , hrejivé slniečko a nádherné lúky plné kvetov .|[ADV, PROPN, ADV, VERB, ADP, NOUN, CCONJ, VERB, PUNCT, VERB, ADJ, ADJ, NOUN, PUNCT, PROPN, PUNCT, ADJ, NOUN, CCONJ, ADJ, NOUN, ADJ, NOUN, PUNCT]|
+--------------------------------------------------------------------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+
Model Information
| Model Name: | pos_snk |
| Compatibility: | Spark NLP 2.7.5+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [pos] |
| Language: | sk |
Data Source
The model was trained on the Universal Dependencies data set.
Benchmarking
| | precision | recall | f1-score | support |
|--------------|-----------|--------|----------|---------|
| ADJ | 0.91 | 0.91 | 0.91 | 1711 |
| ADP | 0.99 | 0.99 | 0.99 | 1188 |
| ADV | 0.82 | 0.82 | 0.82 | 442 |
| AUX | 0.96 | 0.93 | 0.94 | 302 |
| CCONJ | 0.97 | 0.92 | 0.95 | 447 |
| DET | 0.94 | 0.95 | 0.94 | 504 |
| NOUN | 0.90 | 0.96 | 0.93 | 3287 |
| NUM | 0.97 | 0.92 | 0.94 | 412 |
| PART | 0.73 | 0.77 | 0.75 | 177 |
| PRON | 0.97 | 0.97 | 0.97 | 380 |
| PROPN | 0.90 | 0.79 | 0.84 | 879 |
| PUNCT | 1.00 | 1.00 | 1.00 | 1806 |
| SCONJ | 0.99 | 0.98 | 0.99 | 182 |
| SYM | 1.00 | 0.14 | 0.25 | 14 |
| VERB | 0.93 | 0.94 | 0.93 | 1176 |
| X | 0.60 | 0.25 | 0.35 | 121 |
| accuracy | | | 0.93 | 13028 |
| macro avg | 0.91 | 0.83 | 0.84 | 13028 |
| weighted avg | 0.93 | 0.93 | 0.93 | 13028 |