public class SentimentPipeline extends Object
The main program has the following options:
-parserModel Which parser model to use, defaults to englishPCFG.ser.gz
-sentimentModel Which sentiment model to use, defaults to sentiment.ser.gz
-file Which file to process.
-fileList A comma separated list of files to process.
-stdin Read one line at a time from stdin.
-output pennTrees: Output trees with scores at each binarized node. vectors: Number tree nodes and print out the vectors. probabilities: Output the scores for different labels for each node. Defaults to printing just the root.
-filterUnknown Remove unknown trees from the input. Only applies to TREES input, in which case the trees must be binarized with sentiment labels
-help Print out help
|Modifier and Type||Method and Description|
Reads an annotation from the given filename using the requested input.
Runs the tree-based sentiment model on some text.
public static List<Annotation> getAnnotations(StanfordCoreNLP tokenizer, edu.stanford.nlp.sentiment.SentimentPipeline.Input inputFormat, String filename, boolean filterUnknown)
Stanford NLP Group