2023-07-28-twitter_xlm_roberta_base_sentiment_en

docs/_posts/veerdhwaj/2023-07-28-twitter_xlm_roberta_base_sentiment_en.md

@@ -1,10 +1,10 @@
 ---
 layout: model
-title: twitter-xlm-roberta-base-sentiment
+title: twitter_xlm_roberta_base_sentiment(Cardiff nlp) (Veer)
 author: veerdhwaj
 name: twitter_xlm_roberta_base_sentiment
 date: 2023-07-28
-tags: [sentiment, roberta, en, open_source, tensorflow]
+tags: [en, open_source, tensorflow]
 task: Text Classification
 language: en
 edition: Spark NLP 5.0.0
@@ -19,18 +19,21 @@ use_language_switcher: "Python-Scala-Java"
 
 ## Description
 
-This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages
-Huggingface : https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment
+This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages (see paper for details).
+
+Paper: XLM-T: A Multilingual Language Model Toolkit for Twitter.
+Git Repo: XLM-T official repository.
+This model has been integrated into the TweetNLP library.
 
 ## Predicted Entities
 
-`sentiment`
+
 
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
-[Download](https://s3.amazonaws.com/community.johnsnowlabs.com/veerdhwaj/twitter_xlm_roberta_base_sentiment_en_5.0.0_3.2_1690535217423.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
-[Copy S3 URI](s3://community.johnsnowlabs.com/veerdhwaj/twitter_xlm_roberta_base_sentiment_en_5.0.0_3.2_1690535217423.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+[Download](https://s3.amazonaws.com/community.johnsnowlabs.com/veerdhwaj/twitter_xlm_roberta_base_sentiment_en_5.0.0_3.2_1690542160993.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://community.johnsnowlabs.com/veerdhwaj/twitter_xlm_roberta_base_sentiment_en_5.0.0_3.2_1690542160993.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
 
 ## How to use
 
@@ -39,34 +42,33 @@ Huggingface : https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentime
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}
 ```python
-import spark.implicits._
-import com.johnsnowlabs.nlp.base._
-import com.johnsnowlabs.nlp.annotator._
-import org.apache.spark.ml.Pipeline
+from pyspark.ml import Pipeline
 
-val documentAssembler = new DocumentAssembler()
-  .setInputCol("text")
-  .setOutputCol("document")
+document_assembler = DocumentAssembler() \
+    .setInputCol('text') \
+    .setOutputCol('document')
 
-val tokenizer = new Tokenizer()
-  .setInputCols("document")
-  .setOutputCol("token")
+tokenizer = Tokenizer() \
+    .setInputCols(['document']) \
+    .setOutputCol('token')
 
-val sequenceClassifier = XlmRoBertaForSequenceClassification.pretrained('twitter_xlm_roberta_base_sentiment')
-  .setInputCols("token", "document")
+sequenceClassifier = XlmRoBertaForSequenceClassification.pretrained('twitter_xlm_roberta_base_sentiment')\
+  .setInputCols(["document",'token'])\
   .setOutputCol("class")
-  .setCaseSensitive(true)
 
-val pipeline = new Pipeline().setStages(Array(
-  documentAssembler,
-  tokenizer,
-  sequenceClassifier
-))
+pipeline = Pipeline(stages=[
+    document_assembler, 
+    tokenizer,
+    sequenceClassifier    
+])
+
+# couple of simple examples
+example = spark.createDataFrame([['사랑해!'], ["T'estimo! ❤️"], ["I love you!"], ['Mahal kita!']]).toDF("text")
 
-val data = Seq("I loved this movie when I was a child.", "It was pretty boring.").toDF("text")
-val result = pipeline.fit(data).transform(data)
+result = pipeline.fit(example).transform(example)
 
-result.select("class.result").show(false)
+# result is a DataFrame
+result.select("text", "class.result").show()
 ```
 
 </div>

docs/_posts/veerdhwaj/2023-07-31-twitter_xlm_roberta_base_sentiment_pdc_en.md

@@ -0,0 +1,86 @@
+---
+layout: model
+title: twitter_xlm_roberta_base_sentiment_pdc(cardiff)
+author: veerdhwaj
+name: twitter_xlm_roberta_base_sentiment_pdc
+date: 2023-07-31
+tags: [en, open_source, tensorflow]
+task: Text Classification
+language: en
+edition: Spark NLP 5.0.0
+spark_version: 3.2
+supported: false
+engine: tensorflow
+annotator: XlmRoBertaForSequenceClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Huggingface model: https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/community.johnsnowlabs.com/veerdhwaj/twitter_xlm_roberta_base_sentiment_pdc_en_5.0.0_3.2_1690779049644.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://community.johnsnowlabs.com/veerdhwaj/twitter_xlm_roberta_base_sentiment_pdc_en_5.0.0_3.2_1690779049644.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+from pyspark.ml import Pipeline
+
+document_assembler = DocumentAssembler() \
+    .setInputCol('text') \
+    .setOutputCol('document')
+
+tokenizer = Tokenizer() \
+    .setInputCols(['document']) \
+    .setOutputCol('token')
+
+sequenceClassifier = XlmRoBertaForSequenceClassification.pretrained('twitter_xlm_roberta_base_sentiment_pdc')\
+  .setInputCols(["document",'token'])\
+  .setOutputCol("class")
+
+pipeline = Pipeline(stages=[
+    document_assembler, 
+    tokenizer,
+    sequenceClassifier    
+])
+
+# couple of simple examples
+example = spark.createDataFrame([['사랑해!'], ["T'estimo! ❤️"], ["I love you!"], ['Mahal kita!']]).toDF("text")
+
+result = pipeline.fit(example).transform(example)
+
+# result is a DataFrame
+result.select("text", "class.result").show()
+```
+
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|twitter_xlm_roberta_base_sentiment_pdc|
+|Compatibility:|Spark NLP 5.0.0+|
+|License:|Open Source|
+|Edition:|Community|
+|Input Labels:|[document, token]|
+|Output Labels:|[class]|
+|Language:|en|
+|Size:|1.0 GB|
+|Case sensitive:|true|
+|Max sentence length:|512|