Upload 75 files

.streamlit/config.toml

@@ -0,0 +1,3 @@
+[theme]
+base="light"
+primaryColor="#29B4E8"

Demo.py

@@ -0,0 +1,149 @@
+import streamlit as st
+import sparknlp
+import os
+
+from sparknlp.base import *
+from sparknlp.common import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+from sparknlp.pretrained import PretrainedPipeline
+
+# Page Configuration
+st.set_page_config(
+    layout="wide", 
+    initial_sidebar_state="auto"
+)
+
+# Custom CSS for Styling
+st.markdown("""
+    <style>
+        .main-title {
+            font-size: 36px;
+            color: #4A90E2;
+            font-weight: bold;
+            text-align: center;
+        }
+        .section {
+            background-color: #f9f9f9;
+            padding: 10px;
+            border-radius: 10px;
+            margin-top: 10px;
+        }
+        .section p, .section ul {
+            color: #666666;
+        }
+    </style>
+""", unsafe_allow_html=True)
+
+# Initialize Spark NLP
+@st.cache_resource
+def init_spark():
+    return sparknlp.start()
+
+# Create a Spark NLP Pipeline for MarianTransformer
+@st.cache_resource
+def create_pipeline(model_name):
+    document_assembler = DocumentAssembler()\
+        .setInputCol("text")\
+        .setOutputCol("document")
+
+    sentence_detector = SentenceDetectorDLModel()\
+        .pretrained("sentence_detector_dl", "xx")\
+        .setInputCols(["document"])\
+        .setOutputCol("sentences")
+
+    marian_translator = MarianTransformer.pretrained(model_name, "xx")\
+        .setInputCols(["sentences"])\
+        .setOutputCol("translation")
+
+    return Pipeline(stages=[document_assembler, sentence_detector, marian_translator])
+
+# Process the Input Text Through the Pipeline
+def fit_data(pipeline, text):
+    data = spark.createDataFrame([[text]]).toDF("text")
+    result = pipeline.fit(data).transform(data)
+    return result.select('translation.result').collect()
+
+# Title and Subtitle
+title = 'Multilingual Text Translation with Spark NLP and MarianMT'
+sub_title = """
+The MarianTransformer is a powerful, state-of-the-art machine translation model based on the Transformer architecture. Developed by the MarianMT project, this annotator supports over 1,000 translation directions, making it one of the most versatile tools for multilingual natural language processing. Integrated within Spark NLP, the MarianTransformer Annotator allows for scalable and efficient text translation, leveraging the parallel processing capabilities of Apache Spark. Whether you're translating large documents or handling multiple languages simultaneously, this tool ensures high-quality translations with minimal latency.
+"""
+
+st.markdown(f'<div class="main-title">{title}</div>', unsafe_allow_html=True)
+st.markdown(f'<div class="section"><p>{sub_title}</p></div>', unsafe_allow_html=True)
+
+# Mapping Models to Descriptions
+model_mappings = {
+    "opus_mt_en_fr": "Translate text from English to French",
+    "opus_mt_en_it": "Translate text from English to Italian",
+    "opus_mt_en_es": "Translate text from English to Spanish",
+    "opus_mt_en_de": "Translate text from English to German",
+    "opus_mt_en_cpp": "Translate text from English to Portuguese",
+    "opus_mt_fr_en": "Translate text from French to English",
+    "opus_mt_it_en": "Translate text from Italian to English",
+    "opus_mt_es_en": "Translate text from Spanish to English",
+    "opus_mt_de_en": "Translate text from German to English",
+    "opus_mt_cpp_en": "Translate text from Portuguese to English"
+}
+
+# Sidebar for Language Selection
+st.sidebar.title("Language Selection")
+
+language_mapping = {
+    "English": 'en', 
+    "French": 'fr', 
+    "Italian": 'it', 
+    "Spanish": 'es', 
+    "German": 'de', 
+    "Portuguese": 'cpp'
+}
+
+from_language = st.sidebar.selectbox("Translate From", list(language_mapping.keys()))
+
+if from_language == 'English':
+    to_language = st.sidebar.selectbox("Translate To", ['French', 'Italian', 'Spanish', 'German', 'Portuguese'])
+else:
+    to_language = st.sidebar.selectbox("Translate To", ['English'])
+
+selected_model = f'opus_mt_{language_mapping[from_language]}_{language_mapping[to_language]}'
+st.subheader(model_mappings[selected_model])
+
+# Reference Notebook Link in Sidebar
+link= """<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/TRANSLATION_MARIAN.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" style="zoom: 1.3" alt="Open In Colab"/></a>"""
+st.sidebar.title('')
+st.sidebar.markdown('Reference notebook:')
+st.sidebar.markdown(link, unsafe_allow_html=True)
+
+# Load Sample Text Files
+folder_path = f"inputs/{selected_model}"
+examples = [
+    lines[1].strip() 
+    for filename in os.listdir(folder_path) 
+    if filename.endswith('.txt') 
+    for lines in [open(os.path.join(folder_path, filename), 'r', encoding='utf-8').readlines()] 
+    if len(lines) >= 2
+]
+
+selected_text = st.selectbox("Select a Sample Text", examples)
+custom_input = st.text_input("Try it for yourself!")
+
+if custom_input:
+    selected_text = custom_input
+
+# Display the Selected or Entered Text
+st.subheader('Selected Text')
+st.write(selected_text)
+
+# Perform Translation and Display the Result
+st.subheader("Translation Result")
+
+spark = init_spark()
+pipeline = create_pipeline(selected_model)
+output = fit_data(pipeline, selected_text)
+
+res = "".join(output[0][0])
+HTML_WRAPPER = """<div class="scroll entities" style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem; white-space:pre-wrap">{}</div>"""
+st.markdown(HTML_WRAPPER.format(res), unsafe_allow_html=True)
+
+

Dockerfile

@@ -0,0 +1,72 @@
+# Download base image ubuntu 18.04
+FROM ubuntu:18.04
+
+# Set environment variables
+ENV NB_USER jovyan
+ENV NB_UID 1000
+ENV HOME /home/${NB_USER}
+ENV JAVA_HOME /usr/lib/jvm/java-8-openjdk-amd64/
+
+# Install required packages
+RUN apt-get update && apt-get install -y \
+    tar \
+    wget \
+    bash \
+    rsync \
+    gcc \
+    libfreetype6-dev \
+    libhdf5-serial-dev \
+    libpng-dev \
+    libzmq3-dev \
+    python3 \
+    python3-dev \
+    python3-pip \
+    unzip \
+    pkg-config \
+    software-properties-common \
+    graphviz \
+    openjdk-8-jdk \
+    ant \
+    ca-certificates-java \
+    && apt-get clean \
+    && update-ca-certificates -f
+
+# Install Python 3.8 and pip
+RUN add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt-get install -y python3.8 python3-pip \
+    && apt-get clean
+
+# Set up JAVA_HOME
+RUN echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> /etc/profile \
+    && echo "export PATH=\$JAVA_HOME/bin:\$PATH" >> /etc/profile
+# Create a new user named "jovyan" with user ID 1000
+RUN useradd -m -u ${NB_UID} ${NB_USER}
+
+# Switch to the "jovyan" user
+USER ${NB_USER}
+
+# Set home and path variables for the user
+ENV HOME=/home/${NB_USER} \
+    PATH=/home/${NB_USER}/.local/bin:$PATH
+
+# Set up PySpark to use Python 3.8 for both driver and workers
+ENV PYSPARK_PYTHON=/usr/bin/python3.8
+ENV PYSPARK_DRIVER_PYTHON=/usr/bin/python3.8
+
+# Set the working directory to the user's home directory
+WORKDIR ${HOME}
+
+# Upgrade pip and install Python dependencies
+RUN python3.8 -m pip install --upgrade pip
+COPY requirements.txt /tmp/requirements.txt
+RUN python3.8 -m pip install -r /tmp/requirements.txt
+
+# Copy the application code into the container at /home/jovyan
+COPY --chown=${NB_USER}:${NB_USER} . ${HOME}
+
+# Expose port for Streamlit
+EXPOSE 7860
+
+# Define the entry point for the container
+ENTRYPOINT ["streamlit", "run", "Demo.py", "--server.port=7860", "--server.address=0.0.0.0"]

inputs/opus_mt_cpp_en/Example1.txt

@@ -0,0 +1,2 @@
+Example1.txt
+Além de ser o rei do norte, John Snow é um médico inglês e líder no desenvolvimento de anestesia e higiene médica. Ele é considerado o primeiro a usar dados para curar surto de cólera em 1854.

inputs/opus_mt_cpp_en/Example2.txt

@@ -0,0 +1,2 @@
+Example2.txt
+Titanic é um romance épico americano de 1997, um filme de desastre dirigido, escrito, co-produzido e co-editado por James Cameron. Incorporando aspectos históricos e ficcionalizados, é baseado em relatos do naufrágio do RMS Titanic. É estrelado por Leonardo DiCaprio e Kate Winslet como membros de diferentes classes sociais que se apaixonam a bordo do navio durante sua viagem inaugural malfadada.

inputs/opus_mt_cpp_en/Example3.txt

@@ -0,0 +1,2 @@
+Example3.txt
+William Henry Gates III (nascido em 28 de outubro de 1955) é um magnata dos negócios, desenvolvedor de software, investidor e filantropo americano. Ele é mais conhecido como o co-fundador da Microsoft Corporation. Durante sua carreira na Microsoft, Gates ocupou os cargos de presidente do conselho, diretor executivo (CEO), presidente e arquiteto-chefe de software. Ele também foi o maior acionista individual até maio de 2014. É um dos mais conhecidos empreendedores e pioneiros da revolução do microcomputador das décadas de 1970 e 1980.

inputs/opus_mt_cpp_en/Example4.txt

@@ -0,0 +1,2 @@
+Example4.txt
+A Mona Lisa é uma pintura a óleo do século 16 criada por Leonardo. É realizado no Louvre, em Paris.

inputs/opus_mt_cpp_en/Example5.txt

@@ -0,0 +1,2 @@
+Example5.txt
+O Facebook é um serviço de rede social lançado como TheFacebook em 4 de fevereiro de 2004. Foi fundado por Mark Zuckerberg com seus colegas de faculdade e colegas da Universidade de Harvard Eduardo Saverin, Andrew McCollum, Dustin Moskovitz e Chris Hughes. A associação do site foi inicialmente limitada pelos fundadores aos alunos de Harvard, mas foi expandida para outras faculdades na área de Boston, a Ivy League e, gradualmente, a maioria das universidades nos Estados Unidos e Canadá.

inputs/opus_mt_cpp_en/Example6.txt

@@ -0,0 +1,2 @@
+Example6.txt
+Geoffrey Everest Hinton é um psicólogo cognitivo e cientista da computação canadense inglês, mais conhecido por seu trabalho em redes neurais artificiais. Desde 2013, ele divide seu tempo trabalhando para o Google e a Universidade de Toronto. Em 2017, ele foi cofundador e se tornou o assessor científico-chefe do Vector Institute em Toronto.

inputs/opus_mt_cpp_en/Example7.txt

@@ -0,0 +1,2 @@
+Example7.txt
+Quando eu disse a John que queria me mudar para o Alasca, ele me avisou que teria problemas para encontrar um Starbucks lá.

inputs/opus_mt_de_en/Example1.txt

@@ -0,0 +1,2 @@
+Example1.txt
+John Snow ist ein englischer Arzt und ein Führer in der Entwicklung der Anästhesie des Nordens.. Er ist der erste, der Daten verwendet, um Choleraausbruch 1854 zu heilen.

inputs/opus_mt_de_en/Example2.txt

@@ -0,0 +1,2 @@
+Example2.txt
+Titanic ist ein US-amerikanischer Film von James Cameron.. Sie umfasst sowohl historische als auch fiktionalisierte Aspekte, basiert auf Konten der Versenken der RMS Titanic.. Es spielt Leonardo DiCaprio und Kate Winslet als Mitglieder der verschiedenen sozialen Klassen. Sie verliebt sich in das Schiff während seiner unglückselige Mädchen.

inputs/opus_mt_de_en/Example3.txt

@@ -0,0 +1,2 @@
+Example3.txt
+Oktober 1955 in New York City) ist ein US-amerikanischer Software-Entwickler, Investor und Philanthrop.. Während seiner Karriere bei Microsoft, Gates war die Positionen von Vorsitzender, Chief Executive Officer (CEO), Präsident und Chef Software Architekt.. Bis Mai 2014 war er der größte Einzelaktionär.. Er ist einer der bekanntesten Unternehmer und Pioniere der Mikrocomputerrevolution der 1970er und 1980er Jahre.

inputs/opus_mt_de_en/Example4.txt

@@ -0,0 +1,2 @@
+Example4.txt
+Die Mona Lisa ist ein Ölgemälde aus dem 16.. Es wird im Louvre in Paris gehalten.

inputs/opus_mt_de_en/Example5.txt

@@ -0,0 +1,2 @@
+Example5.txt
+Facebook ist ein Social Network Service am 4. Februar 2004.. Es wurde von Mark Zuckerberg mit seinen College-Mitbewohnern und anderen Harvard-Universitätsstudenten Eduardo Saverin, Andrew McCollum, Dustin Moskovitz gegründet.. Die Mitgliedschaft der Website wurde zunächst von Harvard Studenten, aber auch auf andere Hochschulen in der Boston, die Ivy League und allmählich die meisten Universitäten in den Vereinigten Staaten

inputs/opus_mt_de_en/Example6.txt

@@ -0,0 +1,2 @@
+Example6.txt
+Geoffrey Everest Hinton ist ein kanadischer Psychologe und Computer.. Seit 2013 arbeitet er für Google und die University of Toronto.. 2017 wurde er wissenschaftlicher Berater des Vector Institute in Toronto.

inputs/opus_mt_de_en/Example7.txt

@@ -0,0 +1,2 @@
+Example7.txt
+Als ich John sagte, dass ich nach Alaska ziehen wollte, dass ich Probleme hatte, dass ich ein Starbucks dort haben würde, er mich, dass ich hatte, dass ich hatte, dass ich

inputs/opus_mt_en_cpp/Example1.txt

@@ -0,0 +1,2 @@
+Example1.txt
+Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1854.

inputs/opus_mt_en_cpp/Example2.txt

@@ -0,0 +1,2 @@
+Example2.txt
+Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage.

inputs/opus_mt_en_cpp/Example3.txt

@@ -0,0 +1,2 @@
+Example3.txt
+William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s.

inputs/opus_mt_en_cpp/Example4.txt

@@ -0,0 +1,2 @@
+Example4.txt
+The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris.

inputs/opus_mt_en_cpp/Example5.txt

@@ -0,0 +1,2 @@
+Example5.txt
+Facebook is a social networking service launched as TheFacebook on February 4, 2004. It was founded by Mark Zuckerberg with his college roommates and fellow Harvard University students Eduardo Saverin, Andrew McCollum, Dustin Moskovitz and Chris Hughes. The website's membership was initially limited by the founders to Harvard students, but was expanded to other colleges in the Boston area, the Ivy League, and gradually most universities in the United States and Canada.

inputs/opus_mt_en_cpp/Example6.txt

@@ -0,0 +1,2 @@
+Example6.txt
+Geoffrey Everest Hinton is an English Canadian cognitive psychologist and computer scientist, most noted for his work on artificial neural networks. Since 2013 he divides his time working for Google and the University of Toronto. In 2017, he cofounded and became the Chief Scientific Advisor of the Vector Institute in Toronto.

inputs/opus_mt_en_cpp/Example7.txt

@@ -0,0 +1,2 @@
+Example7.txt
+When I told John that I wanted to move to Alaska, he warned me that I'd have trouble finding a Starbucks there.

inputs/opus_mt_en_de/Example1.txt

@@ -0,0 +1,2 @@
+Example1.txt
+Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1854.

inputs/opus_mt_en_de/Example2.txt

@@ -0,0 +1,2 @@
+Example2.txt
+Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage.

inputs/opus_mt_en_de/Example3.txt

@@ -0,0 +1,2 @@
+Example3.txt
+William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s.

inputs/opus_mt_en_de/Example4.txt

@@ -0,0 +1,2 @@
+Example4.txt
+The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris.

inputs/opus_mt_en_de/Example5.txt

@@ -0,0 +1,2 @@
+Example5.txt
+Facebook is a social networking service launched as TheFacebook on February 4, 2004. It was founded by Mark Zuckerberg with his college roommates and fellow Harvard University students Eduardo Saverin, Andrew McCollum, Dustin Moskovitz and Chris Hughes. The website's membership was initially limited by the founders to Harvard students, but was expanded to other colleges in the Boston area, the Ivy League, and gradually most universities in the United States and Canada.

inputs/opus_mt_en_de/Example6.txt

@@ -0,0 +1,2 @@
+Example6.txt
+Geoffrey Everest Hinton is an English Canadian cognitive psychologist and computer scientist, most noted for his work on artificial neural networks. Since 2013 he divides his time working for Google and the University of Toronto. In 2017, he cofounded and became the Chief Scientific Advisor of the Vector Institute in Toronto.

inputs/opus_mt_en_de/Example7.txt

@@ -0,0 +1,2 @@
+Example7.txt
+When I told John that I wanted to move to Alaska, he warned me that I'd have trouble finding a Starbucks there.

inputs/opus_mt_en_es/Example1.txt

@@ -0,0 +1,2 @@
+Example1.txt
+Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1854.

inputs/opus_mt_en_es/Example2.txt

@@ -0,0 +1,2 @@
+Example2.txt
+Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage.

inputs/opus_mt_en_es/Example3.txt

@@ -0,0 +1,2 @@
+Example3.txt
+William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s.

inputs/opus_mt_en_es/Example4.txt

@@ -0,0 +1,2 @@
+Example4.txt
+The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris.

inputs/opus_mt_en_es/Example5.txt

@@ -0,0 +1,2 @@
+Example5.txt
+Facebook is a social networking service launched as TheFacebook on February 4, 2004. It was founded by Mark Zuckerberg with his college roommates and fellow Harvard University students Eduardo Saverin, Andrew McCollum, Dustin Moskovitz and Chris Hughes. The website's membership was initially limited by the founders to Harvard students, but was expanded to other colleges in the Boston area, the Ivy League, and gradually most universities in the United States and Canada.

inputs/opus_mt_en_es/Example6.txt

@@ -0,0 +1,2 @@
+Example6.txt
+Geoffrey Everest Hinton is an English Canadian cognitive psychologist and computer scientist, most noted for his work on artificial neural networks. Since 2013 he divides his time working for Google and the University of Toronto. In 2017, he cofounded and became the Chief Scientific Advisor of the Vector Institute in Toronto.

inputs/opus_mt_en_es/Example7.txt

@@ -0,0 +1,2 @@
+Example7.txt
+When I told John that I wanted to move to Alaska, he warned me that I'd have trouble finding a Starbucks there.

inputs/opus_mt_en_fr/Example1.txt

@@ -0,0 +1,2 @@
+Example1.txt
+Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1854.

inputs/opus_mt_en_fr/Example2.txt

@@ -0,0 +1,2 @@
+Example2.txt
+Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage.

inputs/opus_mt_en_fr/Example3.txt

@@ -0,0 +1,2 @@
+Example3.txt
+William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s.

inputs/opus_mt_en_fr/Example4.txt

@@ -0,0 +1,2 @@
+Example4.txt
+The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris.

inputs/opus_mt_en_fr/Example5.txt

@@ -0,0 +1,2 @@
+Example5.txt
+Facebook is a social networking service launched as TheFacebook on February 4, 2004. It was founded by Mark Zuckerberg with his college roommates and fellow Harvard University students Eduardo Saverin, Andrew McCollum, Dustin Moskovitz and Chris Hughes. The website's membership was initially limited by the founders to Harvard students, but was expanded to other colleges in the Boston area, the Ivy League, and gradually most universities in the United States and Canada.

inputs/opus_mt_en_fr/Example6.txt

@@ -0,0 +1,2 @@
+Example6.txt
+Geoffrey Everest Hinton is an English Canadian cognitive psychologist and computer scientist, most noted for his work on artificial neural networks. Since 2013 he divides his time working for Google and the University of Toronto. In 2017, he cofounded and became the Chief Scientific Advisor of the Vector Institute in Toronto.

inputs/opus_mt_en_fr/Example7.txt

@@ -0,0 +1,2 @@
+Example7.txt
+When I told John that I wanted to move to Alaska, he warned me that I'd have trouble finding a Starbucks there.

inputs/opus_mt_en_it/Example1.txt

@@ -0,0 +1,2 @@
+Example1.txt
+Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1854.

inputs/opus_mt_en_it/Example2.txt

@@ -0,0 +1,2 @@
+Example2.txt
+Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage.

inputs/opus_mt_en_it/Example3.txt

@@ -0,0 +1,2 @@
+Example3.txt
+William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s.

inputs/opus_mt_en_it/Example4.txt

@@ -0,0 +1,2 @@
+Example4.txt
+The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris.

inputs/opus_mt_en_it/Example5.txt

@@ -0,0 +1,2 @@
+Example5.txt
+Facebook is a social networking service launched as TheFacebook on February 4, 2004. It was founded by Mark Zuckerberg with his college roommates and fellow Harvard University students Eduardo Saverin, Andrew McCollum, Dustin Moskovitz and Chris Hughes. The website's membership was initially limited by the founders to Harvard students, but was expanded to other colleges in the Boston area, the Ivy League, and gradually most universities in the United States and Canada.