import streamlit as st
# Page configuration
st.set_page_config(
layout="wide",
initial_sidebar_state="auto"
)
# Custom CSS for better styling
st.markdown("""
""", unsafe_allow_html=True)
# Title
st.markdown('Introduction to XLM-RoBERTa Annotators in Spark NLP
', unsafe_allow_html=True)
# Subtitle
st.markdown("""
XLM-RoBERTa (Cross-lingual Robustly Optimized BERT Approach) is an advanced multilingual model that extends the capabilities of RoBERTa to over 100 languages. Pre-trained on a massive, diverse corpus, XLM-RoBERTa is designed to handle various NLP tasks in a multilingual context, making it ideal for applications that require cross-lingual understanding. Below, we provide an overview of the XLM-RoBERTa annotators for these tasks:
""", unsafe_allow_html=True)
st.markdown("""Sequence Classification with XLM-RoBERTa
""", unsafe_allow_html=True)
st.markdown("""
Sequence classification is a common task in Natural Language Processing (NLP) where the goal is to assign a label to a sequence of text, such as sentiment analysis, spam detection, or paraphrase identification.
XLM-RoBERTa excels at sequence classification across multiple languages, making it a powerful tool for global applications. Below is an example of how to implement sequence classification using XLM-RoBERTa in Spark NLP.
Using XLM-RoBERTa for Sequence Classification enables:
- Multilingual Text Classification: Classify sequences of text in multiple languages with a single model.
- Broad Application: Apply to tasks such as sentiment analysis, spam detection, and paraphrase identification across languages.
- Transfer Learning: Utilize pretrained XLM-RoBERTa models to leverage knowledge from extensive cross-lingual datasets.
Advantages of using XLM-RoBERTa for Sequence Classification in Spark NLP include:
- Scalability: Spark NLP is built on Apache Spark, ensuring it scales efficiently for large datasets.
- Pretrained Excellence: Leverage state-of-the-art pretrained models to achieve high accuracy in text classification tasks.
- Multilingual Flexibility: XLM-RoBERTa’s multilingual capabilities make it suitable for global applications, reducing the need for language-specific models.
- Seamless Integration: Easily incorporate XLM-RoBERTa into your existing Spark pipelines for streamlined NLP workflows.
""", unsafe_allow_html=True)
st.markdown("""How to Use XLM-RoBERTa for Sequence Classification in Spark NLP
""", unsafe_allow_html=True)
st.markdown("""
To leverage XLM-RoBERTa for sequence classification, Spark NLP provides an intuitive pipeline setup. The following example shows how to use XLM-RoBERTa for sequence classification tasks such as sentiment analysis, paraphrase detection, or categorizing text sequences into predefined classes. XLM-RoBERTa’s multilingual training enables it to perform sequence classification across various languages, making it a powerful tool for global NLP tasks.
""", unsafe_allow_html=True)
# Code Example
st.code('''
from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
documentAssembler = DocumentAssembler() \\
.setInputCol("text") \\
.setOutputCol("document")
tokenizer = Tokenizer() \\
.setInputCols("document") \\
.setOutputCol("token")
seq_classifier = XlmRoBertaForSequenceClassification.pretrained("xlmroberta_classifier_base_mrpc","en") \\
.setInputCols(["document", "token"]) \\
.setOutputCol("class")
pipeline = Pipeline(stages=[documentAssembler, tokenizer, seq_classifier])
data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")
result = pipeline.fit(data).transform(data)
result.select("class.result").show(truncate=False)
''', language='python')
st.text("""
+-------+
|result |
+-------+
|[True] |
+-------+
""")
# Model Info Section
st.markdown('Choosing the Right Model
', unsafe_allow_html=True)
st.markdown("""
The XLM-RoBERTa model used here is pretrained and fine-tuned for sequence classification tasks such as paraphrase detection. It is available in Spark NLP, providing high accuracy and multilingual support.
For more information about the model, visit the XLM-RoBERTa Model Hub.
""", unsafe_allow_html=True)
# References Section
st.markdown('References
', unsafe_allow_html=True)
st.markdown("""
""", unsafe_allow_html=True)
# Footer
st.markdown("""
- Official Website: Documentation and examples
- Slack: Live discussion with the community and team
- GitHub: Bug reports, feature requests, and contributions
- Medium: Spark NLP articles
- YouTube: Video tutorials
""", unsafe_allow_html=True)
st.markdown('Quick Links
', unsafe_allow_html=True)
st.markdown("""
""", unsafe_allow_html=True)