cs-nlp-classical-machine-translation 1.0.1

dotnet add package cs-nlp-classical-machine-translation --version 1.0.1
NuGet\Install-Package cs-nlp-classical-machine-translation -Version 1.0.1
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="cs-nlp-classical-machine-translation" Version="1.0.1" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add cs-nlp-classical-machine-translation --version 1.0.1
#r "nuget: cs-nlp-classical-machine-translation, 1.0.1"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
// Install cs-nlp-classical-machine-translation as a Cake Addin
#addin nuget:?package=cs-nlp-classical-machine-translation&version=1.0.1

// Install cs-nlp-classical-machine-translation as a Cake Tool
#tool nuget:?package=cs-nlp-classical-machine-translation&version=1.0.1

cs-nlp-classical-machine-translation

Classical Machine Translation algorithms such as IBM models and EM methods in .NET

Install

Install-Package cs-nlp-classical-machine-translation

Usage

The sample codes below shows how to train and do language translation with IBM model 1:

using System;
using System.Collections.Generic;
using System.Linq;

namespace ClassicalMachineTranslation
{
    class IBMModel1Demo
    {
        public void RunSimpleTraining()
        {
            IBMModel1 model = new IBMModel1();

            List<SimpleTrainingRecord> training_corpus = new List<SimpleTrainingRecord>();

            EnglishTokenizer tokenizer_output = new EnglishTokenizer();
            FrenchTokenizer tokenizer_input = new FrenchTokenizer();


            SimpleTrainingMethod.Train(model, training_corpus);

            string sentence_input = "[Some French Sentence]";
            string sentence_output = "[Some English Sentence]";

            string[] input_lang = tokenizer_input.Tokenize(sentence_input);
            string[] output_lang = tokenizer_output.Tokenize(sentence_output);
            int[] alignment = model.GetAlignment(input_lang, output_lang);

            Dictionary<int, string> output_mapping = new Dictionary<int, string>();
            int m_input_len = input_lang.Length;
            for (int j = 0; j < m_input_len; ++j)
            {
                int a_j = alignment[j];
                string output_word = output_lang[a_j];
                output_mapping[a_j] = output_word;
            }
            List<int> output_sentence_index_list = output_mapping.Keys.ToList();
            output_sentence_index_list.Sort();

            string[] predicted_output_lang = new string[output_sentence_index_list.Count];
            for (int i = 0; i < predicted_output_lang.Length; ++i)
            {
                predicted_output_lang[i] = output_mapping[output_sentence_index_list[i]];
            }

            Console.WriteLine("Original French Sentence: {0}", sentence_input);
            Console.WriteLine("Predicted English Translation: {0}", string.Join(" ", predicted_output_lang));
        }
        
        public void RunEMTraining()
        {
            IBMModel1 model = new IBMModel1();

            List<EMTrainingRecord> training_corpus = new List<EMTrainingRecord>();

            EnglishTokenizer tokenizer_output = new EnglishTokenizer();
            FrenchTokenizer tokenizer_input = new FrenchTokenizer();

            EMTrainingMethod.Train(model, training_corpus, 20);

            string sentence_input = "[Some French Sentence]";
            string sentence_output = "[Some English Sentence]";

            string[] input_lang = tokenizer_input.Tokenize(sentence_input);
            string[] output_lang = tokenizer_output.Tokenize(sentence_output);
            int[] alignment = model.GetAlignment(input_lang, output_lang);

            Dictionary<int, string> output_mapping = new Dictionary<int, string>();
            int m_input_len = input_lang.Length;
            for (int j = 0; j < m_input_len; ++j)
            {
                int a_j = alignment[j];
                string output_word = output_lang[a_j];
                output_mapping[a_j] = output_word;
            }
            List<int> output_sentence_index_list = output_mapping.Keys.ToList();
            output_sentence_index_list.Sort();

            string[] predicted_output_lang = new string[output_sentence_index_list.Count];
            for (int i = 0; i < predicted_output_lang.Length; ++i)
            {
                predicted_output_lang[i] = output_mapping[output_sentence_index_list[i]];
            }

            Console.WriteLine("Original French Sentence: {0}", sentence_input);
            Console.WriteLine("Predicted English Translation: {0}", string.Join(" ", predicted_output_lang));
        }
    }
}

The sample codes below show how to train and do language translation using IBM model 2:

uusing System;
using System.Collections.Generic;
using System.Linq;

namespace ClassicalMachineTranslation
{
    class IBMModel2Demo
    {
        public void RunSimpleTraining()
        {
            IBMModel2 model = new IBMModel2();

            List<SimpleTrainingRecord> training_corpus = new List<SimpleTrainingRecord>();

            EnglishTokenizer tokenizer_output = new EnglishTokenizer();
            FrenchTokenizer tokenizer_input = new FrenchTokenizer();

            SimpleTrainingMethod.Train(model, training_corpus);

            string sentence_input = "[Some French Sentence]";
            string sentence_output = "[Some English Sentence]";

            string[] input_lang = tokenizer_input.Tokenize(sentence_input);
            string[] output_lang = tokenizer_output.Tokenize(sentence_output);
            int[] alignment = model.GetAlignment(input_lang, output_lang);

            Dictionary<int, string> output_mapping = new Dictionary<int, string>();
            int m_input_len = input_lang.Length;
            for (int j = 0; j < m_input_len; ++j)
            {
                int a_j = alignment[j];
                string output_word = output_lang[a_j];
                output_mapping[a_j] = output_word;
            }
            List<int> output_sentence_index_list = output_mapping.Keys.ToList();
            output_sentence_index_list.Sort();

            string[] predicted_output_lang = new string[output_sentence_index_list.Count];
            for (int i = 0; i < predicted_output_lang.Length; ++i)
            {
                predicted_output_lang[i] = output_mapping[output_sentence_index_list[i]];
            }

            Console.WriteLine("Original French Sentence: {0}", sentence_input);
            Console.WriteLine("Predicted English Translation: {0}", string.Join(" ", predicted_output_lang));
        }
        
        public void RunEMTraining()
        {
            IBMModel2 model = new IBMModel2();

            List<EMTrainingRecord> training_corpus = new List<EMTrainingRecord>();

            EnglishTokenizer tokenizer_output = new EnglishTokenizer();
            FrenchTokenizer tokenizer_input = new FrenchTokenizer();


            EMTrainingMethod.Train(model, training_corpus, 20);

            string sentence_input = "[Some French Sentence]";
            string sentence_output = "[Some English Sentence]";

            string[] input_lang = tokenizer_input.Tokenize(sentence_input);
            string[] output_lang = tokenizer_output.Tokenize(sentence_output);
            int[] alignment = model.GetAlignment(input_lang, output_lang);

            Dictionary<int, string> output_mapping = new Dictionary<int, string>();
            int m_input_len = input_lang.Length;
            for (int j = 0; j < m_input_len; ++j)
            {
                int a_j = alignment[j];
                string output_word = output_lang[a_j];
                output_mapping[a_j] = output_word;
            }
            List<int> output_sentence_index_list = output_mapping.Keys.ToList();
            output_sentence_index_list.Sort();

            string[] predicted_output_lang = new string[output_sentence_index_list.Count];
            for (int i = 0; i < predicted_output_lang.Length; ++i)
            {
                predicted_output_lang[i] = output_mapping[output_sentence_index_list[i]];
            }

            Console.WriteLine("Original French Sentence: {0}", sentence_input);
            Console.WriteLine("Predicted English Translation: {0}", string.Join(" ", predicted_output_lang));
        }
    }
}

Product Compatible and additional computed target framework versions.
.NET Framework net461 is compatible.  net462 was computed.  net463 was computed.  net47 was computed.  net471 was computed.  net472 was computed.  net48 was computed.  net481 was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

This package has no dependencies.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last updated
1.0.1 1,075 4/30/2018

Classicial Machine Translation such as IBM model 1 and IBM model 2 implemented in .NET 4.6.1