| Package | Description |
|---|---|
| edu.nyu.jet.hmm |
The HMM package includes the classes for Hidden Markov Models,
and part-of-speech and name taggers implemented using HMMs. A separate
description is available of the overall structure and external representation
of these models, provided for those who wish to modify the models.
|
| edu.nyu.jet.refres |
The Refres package provides the methods for identifying coreference
relations within a document.
|
| edu.nyu.jet.scorer |
The Scorer package provides the classes for scoring an annotated
document against an answer key..
|
| edu.nyu.jet.tipster |
The Tipster package provides the basic methods for recording
information about documents. It is loosely based on the 'Tipster
Architecture' developed by R.Grishman as part of the Government-sponsored
Tipster program. The basic objects are Documents and Annotations;
a Document is a container for the text of the document, and a set of Annotations
on the Document.
|
| Modifier and Type | Method and Description |
|---|---|
void |
HMMannotator.train(DocumentCollection col)
use the annotations on all documents in DocumentCollection 'col'
to train HMM 'h'.
|
| Modifier and Type | Method and Description |
|---|---|
static void |
CorefCompare.compareCollections(DocumentCollection response,
DocumentCollection key)
compare the entity annotations (coreference) in all documents in
Document Collections 'response' and 'key', updating the documents
in DocumentCollection 'response'.
|
| Modifier and Type | Method and Description |
|---|---|
static void |
NEScorer.scoreCollection(NameTagger tagger,
DocumentCollection testCol,
DocumentCollection keyCol,
String[] tagsToScore)
computes the recall/precision of 'testCollection' with respect to
'keyCollection' (which should have the same documents) with respect
to the name annotations in 'tagsToScore'.
|
| Constructor and Description |
|---|
CollectionView(DocumentCollection col)
create a viewer for Collection 'col'.
|
Copyright © 2016 New York University. All rights reserved.