/// <summary>
/// Initializes a new instance of the <see cref="SentenceDetectorEvaluator"/> class.
/// </summary>
/// <param name="sentenceDetector">The sentence detector.</param>
/// <param name="listeners">The evaluation sample listeners.</param>
public SentenceDetectorEvaluator(
ISentenceDetector sentenceDetector,
params IEvaluationMonitor <SentenceSample>[] listeners) : base(listeners)
{
this.sentenceDetector = sentenceDetector;
FMeasure = new FMeasure <Span>();
}
/// <summary>
/// Summarizes the specified input using the specified <paramref name="sentenceDetector"/> and <paramref name="tokenizer"/>.
/// </summary>
/// <param name="input">The input string to be summarized.</param>
/// <param name="sentenceDetector">The sentence detector.</param>
/// <param name="tokenizer">The tokenizer.</param>
/// <returns>The summarized string.</returns>
/// <exception cref="System.ArgumentNullException">
/// <paramref name="sentenceDetector"/>
/// or
/// <paramref name="tokenizer"/>
/// </exception>
public string Summarize(string input, ISentenceDetector sentenceDetector, ITokenizer tokenizer)
{
if (string.IsNullOrEmpty(input))
{
return(string.Empty);
}
if (sentenceDetector == null)
{
throw new ArgumentNullException(nameof(sentenceDetector));
}
if (tokenizer == null)
{
throw new ArgumentNullException(nameof(tokenizer));
}
var doc = new Document("x-unspecified", input);
var anl = new AggregateAnalyzer {
new SentenceDetectorAnalyzer(sentenceDetector),
new TokenizerAnalyzer(tokenizer)
};
anl.Analyze(doc);
return(ProcessSummarization(doc));
}
/// <summary>
/// Initializes a new instance of the <see cref="AbstractAnalyzer" /> with the specified weight.
/// </summary>
/// <param name="sentenceDetector">The sentence detector.</param>
/// <param name="weight">The analyzer weight.</param>
/// <exception cref="System.ArgumentNullException">
/// <paramref name="sentenceDetector"/>
/// </exception>
public SentenceDetectorAnalyzer(ISentenceDetector sentenceDetector, float weight)
: base(weight) {
if (sentenceDetector == null)
throw new ArgumentNullException("sentenceDetector");
SentenceDetector = sentenceDetector;
}
public WikimediaSentencesReader(List <string> localDumpFilePaths, Predicate <string> pageFilterer, WikiMarkupCleaner wikiMarkupCleaner,
ISentenceDetector sentenceDetector)
{
this.xmlDumpFileReaders = localDumpFilePaths.Select(dp => new XmlDumpFileReader(dp)).ToList();
currentReaderIndex = 0;
this.pageFilterer = pageFilterer;
this.sentenceDetector = sentenceDetector;
this.wikiMarkupCleaner = wikiMarkupCleaner;
}
public NLPToolsController()
{
string modelPath = @"C:\Users\Garrett\Documents\Visual Studio 2015\Projects\MindysTermExtractionLibrary\src\sharpnlp-nbin-files\";
sentenceDetector = new EnglishMaximumEntropySentenceDetector(modelPath + "EnglishSD.nbin");
tokenizer = new EnglishMaximumEntropyTokenizer(modelPath + "EnglishTok.nbin");
posTagger = new EnglishMaximumEntropyPosTagger(modelPath + "EnglishPOS.nbin");
phraseChunker = new EnglishTreebankChunker(modelPath + "EnglishChunk.nbin");
}
/// <summary>
/// Initializes a new instance of the <see cref="AbstractAnalyzer" /> with the specified weight.
/// </summary>
/// <param name="sentenceDetector">The sentence detector.</param>
/// <param name="weight">The analyzer weight.</param>
/// <exception cref="System.ArgumentNullException">
/// <paramref name="sentenceDetector"/>
/// </exception>
public SentenceDetectorAnalyzer(ISentenceDetector sentenceDetector, float weight)
: base(weight)
{
if (sentenceDetector == null)
{
throw new ArgumentNullException("sentenceDetector");
}
SentenceDetector = sentenceDetector;
}
/// <summary>
/// Initializes a new instance of the <see cref="Pipeline"/> class.
/// </summary>
/// <param name="normalizerManager">The normalizer manager.</param>
/// <param name="pOSTagger">The p os tagger.</param>
/// <param name="sentenceDetector">The sentence detector.</param>
/// <param name="stemmer">The stemmer.</param>
/// <param name="stopWordsManager">The stop words manager.</param>
/// <param name="tokenizer">The tokenizer.</param>
/// <param name="featureExtractor">The feature extractor.</param>
/// <param name="textSummarizer">The text summarizer.</param>
/// <param name="entityFinder">The entity finder.</param>
/// <exception cref="ArgumentNullException">
/// normalizerManager or pOSTagger or sentenceDetector or stemmer or stopWordsManager or
/// tokenizer or featureExtractor or textSummarizer
/// </exception>
public Pipeline(
INormalizerManager normalizerManager,
IPOSTagger pOSTagger,
ISentenceDetector sentenceDetector,
IStemmer stemmer,
IStopWordsManager stopWordsManager,
ITokenizer tokenizer,
IFeatureExtractor featureExtractor,
ITextSummarizer textSummarizer,
IEntityFinder entityFinder)
{
NormalizerManager = normalizerManager ?? throw new ArgumentNullException(nameof(normalizerManager));
POSTagger = pOSTagger ?? throw new ArgumentNullException(nameof(pOSTagger));
SentenceDetector = sentenceDetector ?? throw new ArgumentNullException(nameof(sentenceDetector));
Stemmer = stemmer ?? throw new ArgumentNullException(nameof(stemmer));
StopWordsManager = stopWordsManager ?? throw new ArgumentNullException(nameof(stopWordsManager));
Tokenizer = tokenizer ?? throw new ArgumentNullException(nameof(tokenizer));
FeatureExtractor = featureExtractor ?? throw new ArgumentNullException(nameof(featureExtractor));
TextSummarizer = textSummarizer ?? throw new ArgumentNullException(nameof(textSummarizer));
EntityFinder = entityFinder ?? throw new ArgumentNullException(nameof(entityFinder));
SetLanguage(Languages.English);
}
/// <summary>
/// Initializes a new instance of the <see cref="SentenceDetectorAnalyzer" /> using the default weight value.
/// </summary>
/// <param name="sentenceDetector">The sentence detector used to analyze the sentences.</param>
/// <exception cref="System.ArgumentNullException">
/// <paramref name="sentenceDetector"/>
/// </exception>
public SentenceDetectorAnalyzer(ISentenceDetector sentenceDetector) : this(sentenceDetector, 0f)
{
}
/// <summary>
/// Summarizes the specified input using the specified <paramref name="sentenceDetector"/> and <paramref name="tokenizer"/>.
/// </summary>
/// <param name="input">The input string to be summarized.</param>
/// <param name="sentenceDetector">The sentence detector.</param>
/// <param name="tokenizer">The tokenizer.</param>
/// <returns>The summarized string.</returns>
/// <exception cref="System.ArgumentNullException">
/// <paramref name="sentenceDetector"/>
/// or
/// <paramref name="tokenizer"/>
/// </exception>
public string Summarize(string input, ISentenceDetector sentenceDetector, ITokenizer tokenizer) {
if (string.IsNullOrEmpty(input))
return string.Empty;
if (sentenceDetector == null)
throw new ArgumentNullException("sentenceDetector");
if (tokenizer == null)
throw new ArgumentNullException("tokenizer");
var doc = new Document("x-unspecified", input);
var anl = new AggregateAnalyzer {
new SentenceDetectorAnalyzer(sentenceDetector),
new TokenizerAnalyzer(tokenizer)
};
anl.Analyze(doc);
return ProcessSummarization(doc);
}
public EnglishTextProcessor(ISentenceDetectorFactory sdFact, ITokenizerFactory tokenizerFact, IStemmerFactory stemmerFact) : base(Language.English)
{
sd = sdFact.GetSentenceDetector(Language);
tokenizer = tokenizerFact.GetTokenizer(Language);
stemmer = stemmerFact.GetStemmer(Language);
}
/// <summary>
/// Initializes a new instance of the <see cref="SentenceDetectorAnalyzer" /> using the default weight value.
/// </summary>
/// <param name="sentenceDetector">The sentence detector used to analyze the sentences.</param>
/// <exception cref="System.ArgumentNullException">
/// <paramref name="sentenceDetector"/>
/// </exception>
public SentenceDetectorAnalyzer(ISentenceDetector sentenceDetector) : this(sentenceDetector, 0f) { }
/// <summary>
/// Initializes a new instance of the <see cref="SentenceDetectorEvaluator"/> class.
/// </summary>
/// <param name="sentenceDetector">The sentence detector.</param>
/// <param name="listeners">The evaluation sample listeners.</param>
public SentenceDetectorEvaluator(
ISentenceDetector sentenceDetector,
params IEvaluationMonitor <SentenceSample>[] listeners) : base(listeners)
{
this.sentenceDetector = sentenceDetector;
}
