/// <exception cref="Javax.Servlet.ServletException"/>
/// <exception cref="System.IO.IOException"/>
public virtual void OutputVisualise(PrintWriter @out, Annotation annotation)
{
// Note: A lot of the HTML generation in this method could/should be
// done at a templating level, but as-of-yet I am not entirely sure how
// this should be done in jsp. Also, a lot of the HTML is unnecessary
// for the other outputs such as pretty print and XML.
// Div for potential error messages when fetching the configuration.
@out.Println("<div id=\"config_error\">");
@out.Println("</div>");
// Insert divs that will be used for each visualisation type.
int visualiserDivPxWidth = 700;
IDictionary <string, string> nameByAbbrv = new LinkedHashMap <string, string>();
nameByAbbrv["pos"] = "Part-of-Speech";
nameByAbbrv["ner"] = "Named Entity Recognition";
nameByAbbrv["coref"] = "Coreference";
nameByAbbrv["basic_dep"] = "Basic Dependencies";
//nameByAbbrv.put("collapsed_dep", "Collapsed dependencies");
nameByAbbrv["collapsed_ccproc_dep"] = "Enhanced Dependencies";
foreach (KeyValuePair <string, string> entry in nameByAbbrv)
{
@out.Println("<h2>" + entry.Value + ":</h2>");
@out.Println("<div id=\"" + entry.Key + "\" style=\"width:" + visualiserDivPxWidth + "px\">");
@out.Println(" <div id=\"" + entry.Key + "_loading\">");
@out.Println(" <p>Loading...</p>");
@out.Println(" </div>");
@out.Println("</div>");
@out.Println(string.Empty);
}
// Time to get the XML data into HTML.
StringWriter xmlOutput = new StringWriter();
pipeline.XmlPrint(annotation, xmlOutput);
xmlOutput.Flush();
// Escape the XML to be embeddable into a Javascript string.
string escapedXml = xmlOutput.ToString().ReplaceAll("\\r\\n|\\r|\\n", string.Empty).Replace("\"", "\\\"");
// Inject the XML results into the HTML to be retrieved by the Javascript.
@out.Println("<script type=\"text/javascript\">");
@out.Println("// <![CDATA[");
@out.Println(" stanfordXML = \"" + escapedXml + "\";");
@out.Println("// ]]>");
@out.Println("</script>");
// Relative brat installation location to CoreNLP.
string bratLocation = "../brat";
// Inject the location variable, we need it in Javascript mode.
@out.Println("<script type=\"text/javascript\">");
@out.Println("// <![CDATA[");
@out.Println(" bratLocation = \"" + bratLocation + "\";");
@out.Println(" webFontURLs = [\n" + " '" + bratLocation + "/static/fonts/Astloch-Bold.ttf',\n" + " '" + bratLocation + "/static/fonts/PT_Sans-Caption-Web-Regular.ttf',\n" + " '" + bratLocation + "/static/fonts/Liberation_Sans-Regular.ttf'];"
);
@out.Println("// ]]>");
@out.Println("</script>");
// Inject the brat stylesheet (removing this line breaks visualisation).
@out.Println("<link rel=\"stylesheet\" type=\"text/css\" href=\"" + bratLocation + "/style-vis.css\"/>");
// Include the Javascript libraries necessary to run brat.
@out.Println("<script type=\"text/javascript\" src=\"" + bratLocation + "/client/lib/head.load.min.js\"></script>");
// Main Javascript that hooks into all that we have introduced so far.
@out.Println("<script type=\"text/javascript\" src=\"brat.js\"></script>");
// Link to brat, I hope this is okay to have here...
@out.Println("<h>Visualisation provided using the " + "<a href=\"http://brat.nlplab.org/\">brat " + "visualisation/annotation software</a>.</h>");
@out.Println("<br/>");
}
/// <summary>Usage: java -cp "*" StanfordCoreNlpDemo [inputFile [outputTextFile [outputXmlFile]]]</summary>
/// <exception cref="System.IO.IOException"/>
public static void Main(string[] args)
{
// set up optional output files
PrintWriter @out;
if (args.Length > 1)
{
@out = new PrintWriter(args[1]);
}
else
{
@out = new PrintWriter(System.Console.Out);
}
PrintWriter xmlOut = null;
if (args.Length > 2)
{
xmlOut = new PrintWriter(args[2]);
}
// Create a CoreNLP pipeline. To build the default pipeline, you can just use:
// StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// Here's a more complex setup example:
// Properties props = new Properties();
// props.put("annotators", "tokenize, ssplit, pos, lemma, ner, depparse");
// props.put("ner.model", "edu/stanford/nlp/models/ner/english.all.3class.distsim.crf.ser.gz");
// props.put("ner.applyNumericClassifiers", "false");
// StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// Add in sentiment
Properties props = new Properties();
props.SetProperty("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref, sentiment");
StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// Initialize an Annotation with some text to be annotated. The text is the argument to the constructor.
Annotation annotation;
if (args.Length > 0)
{
annotation = new Annotation(IOUtils.SlurpFileNoExceptions(args[0]));
}
else
{
annotation = new Annotation("Kosgi Santosh sent an email to Stanford University. He didn't get a reply.");
}
// run all the selected Annotators on this text
pipeline.Annotate(annotation);
// this prints out the results of sentence analysis to file(s) in good formats
pipeline.PrettyPrint(annotation, @out);
if (xmlOut != null)
{
pipeline.XmlPrint(annotation, xmlOut);
}
// Access the Annotation in code
// The toString() method on an Annotation just prints the text of the Annotation
// But you can see what is in it with other methods like toShorterString()
@out.Println();
@out.Println("The top level annotation");
@out.Println(annotation.ToShorterString());
@out.Println();
// An Annotation is a Map with Class keys for the linguistic analysis types.
// You can get and use the various analyses individually.
// For instance, this gets the parse tree of the first sentence in the text.
IList <ICoreMap> sentences = annotation.Get(typeof(CoreAnnotations.SentencesAnnotation));
if (sentences != null && !sentences.IsEmpty())
{
ICoreMap sentence = sentences[0];
@out.Println("The keys of the first sentence's CoreMap are:");
@out.Println(sentence.KeySet());
@out.Println();
@out.Println("The first sentence is:");
@out.Println(sentence.ToShorterString());
@out.Println();
@out.Println("The first sentence tokens are:");
foreach (ICoreMap token in sentence.Get(typeof(CoreAnnotations.TokensAnnotation)))
{
@out.Println(token.ToShorterString());
}
Tree tree = sentence.Get(typeof(TreeCoreAnnotations.TreeAnnotation));
@out.Println();
@out.Println("The first sentence parse tree is:");
tree.PennPrint(@out);
@out.Println();
@out.Println("The first sentence basic dependencies are:");
@out.Println(sentence.Get(typeof(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation)).ToString(SemanticGraph.OutputFormat.List));
@out.Println("The first sentence collapsed, CC-processed dependencies are:");
SemanticGraph graph = sentence.Get(typeof(SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation));
@out.Println(graph.ToString(SemanticGraph.OutputFormat.List));
// Access coreference. In the coreference link graph,
// each chain stores a set of mentions that co-refer with each other,
// along with a method for getting the most representative mention.
// Both sentence and token offsets start at 1!
@out.Println("Coreference information");
IDictionary <int, CorefChain> corefChains = annotation.Get(typeof(CorefCoreAnnotations.CorefChainAnnotation));
if (corefChains == null)
{
return;
}
foreach (KeyValuePair <int, CorefChain> entry in corefChains)
{
@out.Println("Chain " + entry.Key);
foreach (CorefChain.CorefMention m in entry.Value.GetMentionsInTextualOrder())
{
// We need to subtract one since the indices count from 1 but the Lists start from 0
IList <CoreLabel> tokens = sentences[m.sentNum - 1].Get(typeof(CoreAnnotations.TokensAnnotation));
// We subtract two for end: one for 0-based indexing, and one because we want last token of mention not one following.
@out.Println(" " + m + ", i.e., 0-based character offsets [" + tokens[m.startIndex - 1].BeginPosition() + ", " + tokens[m.endIndex - 2].EndPosition() + ")");
}
}
@out.Println();
@out.Println("The first sentence overall sentiment rating is " + sentence.Get(typeof(SentimentCoreAnnotations.SentimentClass)));
}
IOUtils.CloseIgnoringExceptions(@out);
IOUtils.CloseIgnoringExceptions(xmlOut);
}
