GATE 8 使用指南.pdf

发布时间：2022-06-19 发布人：admin 分类：说明书资料大小：6.54M 资料格式：pdf 举报版权申诉

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第1页.png

第1页 / 共698页

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第2页.png

第2页 / 共698页

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第3页.png

第3页 / 共698页

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第4页.png

第4页 / 共698页

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第5页.png

第5页 / 共698页

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第6页.png

第6页 / 共698页

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第7页.png

第7页 / 共698页

99bbb3e1-198d-4efc-8244-db8675548eb5.pdf-第8页.png

第8页 / 共698页

I GATE Basics

Introduction

How to Use this Text

Context

Overview

Developing and Deploying Language Processing Facilities

Built-In Components

Additional Facilities in GATE Developer/Embedded

An Example

Some Evaluations

Recent Changes

Next Release

Version 8.0 (May 2014)

Further reading

Using GATE Embedded within a Tomcat Web Application

Recommended Directory Structure

Configuration Files

Initialization Code

Groovy for GATE

Groovy Scripting Console for GATE

Groovy scripting PR

The Scriptable Controller

Utility methods

Saving Config Data to gate.xml

Annotation merging through the API

Using Resource Helpers to Extend the API

JAPE: Regular Expressions over Annotations

The Left-Hand Side

Matching Entire Annotation Types

Using Features and Values

Using Meta-Properties

Building complex patterns from simple patterns

Matching a Simple Text String

Using Templates

Multiple Pattern/Action Pairs

LHS Macros

Multi-Constraint Statements

Using Context

Negation

Escaping Special Characters

LHS Operators in Detail

Equality Operators

Comparison Operators

Regular Expression Operators

Contextual Operators

Custom Operators

The Right-Hand Side

A Simple Example

Copying Feature Values from the LHS to the RHS

Optional or Empty Labels

RHS Macros

Use of Priority

Using Phases Sequentially

Using Java Code on the RHS

A More Complex Example

Adding a Feature to the Document

Finding the Tokens of a Matched Annotation

Using Named Blocks

Java RHS Overview

Optimising for Speed

Ontology Aware Grammar Transduction

Serializing JAPE Transducer

How to Serialize?

How to Use the Serialized Grammar File?

Notes for Montreal Transducer Users

JAPE Plus

ANNIC: ANNotations-In-Context

Instantiating SSD

Search GUI

Overview

Syntax of Queries

Top Section

Central Section

Bottom Section

Using SSD from GATE Embedded

How to instantiate a searchabledatastore

How to search in this datastore

Performance Evaluation of Language Analysers

Metrics for Evaluation in Information Extraction

Annotation Relations

Cohen's Kappa

Precision, Recall, F-Measure

Macro and Micro Averaging

The Annotation Diff Tool

Performing Evaluation with the Annotation Diff Tool

Creating a Gold Standard with the Annotation Diff Tool

Corpus Quality Assurance

Description of the interface

Step by step usage

Details of the Corpus statistics table

Details of the Document statistics table

GATE Embedded API for the measures

sec:eval:qapr

Corpus Benchmark Tool

Preparing the Corpora for Use

Defining Properties

Running the Tool

The Results

A Plugin Computing Inter-Annotator Agreement (IAA)

IAA for Classification

IAA For Named Entity Annotation

The BDM-Based IAA Scores

A Plugin Computing the BDM Scores for an Ontology

Quality Assurance Summariser for Teamware

Profiling Processing Resources

Overview

Features

Limitations

Graphical User Interface

Command Line Interface

Application Programming Interface

Log4j.properties

Benchmark log format

Enabling profiling

Reporting tool

Developing GATE

Reporting Bugs and Requesting Features

Contributing Patches

Creating New Plugins

What to Call your Plugin

Writing a New PR

Writing a New VR

Writing a `Ready Made' Application

Distributing Your New Plugins

Updating this User Guide

Building the User Guide

Making Changes to the User Guide

III CREOLE Plugins

Gazetteers

Introduction to Gazetteers

ANNIE Gazetteer

Creating and Modifying Gazetteer Lists

ANNIE Gazetteer Editor

OntoGazetteer

Gaze Ontology Gazetteer Editor

The Gaze Gazetteer List and Mapping Editor

The Gaze Ontology Editor

Hash Gazetteer

Prerequisites

Parameters

Flexible Gazetteer

Gazetteer List Collector

OntoRoot Gazetteer

How Does it Work?

Initialisation of OntoRoot Gazetteer

Simple steps to run OntoRoot Gazetteer

Large KB Gazetteer

Quick usage overview

Dictionary setup

Additional dictionary configuration

Dictionary for Gazetteer List Files

Processing Resource Configuration

Runtime configuration

Semantic Enrichment PR

The Shared Gazetteer for multithreaded processing

Working with Ontologies

Data Model for Ontologies

Hierarchies of Classes and Restrictions

Instances

Hierarchies of Properties

URIs

Ontology Event Model

What Happens when a Resource is Deleted?

The Ontology Plugin: Current Implementation

The OWLIMOntology Language Resource

The ConnectSesameOntology Language Resource

The CreateSesameOntology Language Resource

The OWLIM2 Backwards-Compatible Language Resource

Using Ontology Import Mappings

Using BigOWLIM

The sesameCLI command line interface

The Ontology_OWLIM2 plugin: backwards-compatible implementation

The OWLIMOntologyLR Language Resource

GATE Ontology Editor

Ontology Annotation Tool

Viewing Annotated Text

Editing Existing Annotations

Adding New Annotations

Options

Relation Annotation Tool

Description of the two views

Create new annotation and instance from text selection

Create new annotation and add label to existing instance from text selection

Create and set properties for annotation relation

Delete instance, label or property

Differences with OAT and Ontology Editor

Using the ontology API

Using the ontology API (old version)

Ontology-Aware JAPE Transducer

Annotating Text with Ontological Information

Populating Ontologies

Ontology API and Implementation Changes

Differences between the implementation plugins

Changes in the Ontology API

Non-English Language Support

Language Identification

Fingerprint Generation

French Plugin

German Plugin

Romanian Plugin

Arabic Plugin

Chinese Plugin

Chinese Word Segmentation

Hindi Plugin

Russian Plugin

Bulgarian Plugin

Domain Specific Resources

Biomedical Support

ABNER

MetaMap

GSpell biomedical spelling suggestion and correction

BADREX

MiniChem/Drug Tagger

AbGene

GENIA

Penn BioTagger

MutationFinder

NormaGene

Tools for Social Media Data

Tools for Twitter

Twitter JSON format

Low-level PRs for Tweets

Handling multi-word hashtags

The TwitIE Pipeline

Parsers

MiniPar Parser

Platform Supported

Resources

Parameters

Prerequisites

Grammatical Relationships

RASP Parser

SUPPLE Parser

Requirements

Building SUPPLE

Running the Parser in GATE

Viewing the Parse Tree

System Properties

Configuration Files

Parser and Grammar

Mapping Named Entities

Upgrading from BuChart to SUPPLE

Stanford Parser

Input Requirements

Initialization Parameters

Runtime Parameters

Machine Learning

ML Generalities

Some Definitions

GATE-Specific Interpretation of the Above Definitions

Batch Learning PR

Batch Learning PR Configuration File Settings

Case Studies for the Three Learning Types

How to Use the Batch Learning PR in GATE Developer

Output of the Batch Learning PR

Using the Batch Learning PR from the API

Machine Learning PR

The DATASET Element

The ENGINE Element

The WEKA Wrapper

The MAXENT Wrapper

The SVM Light Wrapper

Example Configuration File

Tools for Alignment Tasks

Introduction

The Tools

Compound Document

CompoundDocumentFromXml

Compound Document Editor

Composite Document

DeleteMembersPR

SwitchMembersPR

Saving as XML

Alignment Editor

Saving Files and Alignments

Section-by-Section Processing

Crowdsourcing Data with GATE

The Basics

Entity classification

Creating a classification job

Loading data into a job

Importing the results

Entity annotation

Creating an annotation job

Loading data into a job

Importing the results

Combining GATE and UIMA

Embedding a UIMA AE in GATE

Mapping File Format

The UIMA Component Descriptor

Using the AnalysisEnginePR

Embedding a GATE CorpusController in UIMA

Mapping File Format

The GATE Application Definition

Configuring the GATEApplicationAnnotator

More (CREOLE) Plugins

Verb Group Chunker

Noun Phrase Chunker

Differences from the Original

Using the Chunker

TaggerFramework

TreeTagger—Multilingual POS Tagger

GENIA and Double Quotes

Chemistry Tagger

Using the Tagger

Zemanta Semantic Annotation Service

Lupedia Semantic Annotation Service

TextRazor Annotation Service

Annotating Numbers

Numbers in Words and Numbers

Roman Numerals

Annotating Measurements

Annotating and Normalizing Dates

Snowball Based Stemmers

Algorithms

GATE Morphological Analyzer

Rule File

Flexible Exporter

Configurable Exporter

Annotation Set Transfer

Schema Enforcer

Information Retrieval in GATE

Using the IR Functionality in GATE

Using the IR API

Websphinx Web Crawler

Using the Crawler PR

Proxy configuration

WordNet in GATE

The WordNet API

Kea - Automatic Keyphrase Detection

Using the `KEA Keyphrase Extractor' PR

Using Kea Corpora

Annotation Merging Plugin

Copying Annotations between Documents

OpenCalais Plugin

LingPipe Plugin

LingPipe Tokenizer PR

LingPipe Sentence Splitter PR

LingPipe POS Tagger PR

LingPipe NER PR

LingPipe Language Identifier PR

OpenNLP Plugin

Init parameters and models

OpenNLP PRs

Obtaining and generating models

Stanford CoreNLP

Stanford Tagger

Stanford Parser

Stanford Named Entity Recognition

Content Detection Using Boilerpipe

Inter Annotator Agreement

Schema Annotation Editor

Coref Tools Plugin

Pubmed Format

MediaWiki Format

Fast Infoset Document Format

CSV Document Support

TermRaider term extraction tools

Termbank language resources

Termbank Score Copier

The PMI bank language resource

Document Normalizer

Developer Tools

Linguistic Simplifier

IV The GATE Family: Cloud, MIMIR, Teamware

GATE Cloud

GATE Cloud services: an overview

Comparison with other systems

How to buy services

Pricing and discounts

Annotation Jobs on GATECloud.net

The Annotation Service Charges Explained

Annotation Job Execution in Detail

Running Custom Annotation Jobs on GATECloud.net

Preparing Your Application: The Basics

The GATECloud.net environment

GATE Teamware: A Web-based Collaborative Corpus Annotation Tool

Introduction

Requirements for Multi-Role Collaborative Annotation Environments

Typical Division of Labour

Remote, Scalable Data Storage

Automatic annotation services

Workflow Support

Teamware: Architecture, Implementation, and Examples

Data Storage Service

Annotation Services

The Executive Layer

The User Interfaces

Practical Applications

GATE Mímir

Appendices

Change Log

Next Release

October 2014

September 2014

August 2014

July 2014

June 2014

May 2014

Version 8.0 (May 2014)

Major changes

Other new and improved plugins

Bug fixes and other improvements

For developers

Version 7.1 (November 2012)

New plugins

Library updates

GATE Embedded API changes

Version 7.0 (February 2012)

Major new features

Removal of deprecated functionality

Other enhancements and bug fixes

Version 6.1 (April 2011)

New CREOLE Plugins

Other new features and improvements

Version 6.0 (November 2010)

Major new features

Breaking changes

Other new features and bugfixes

Version 5.2.1 (May 2010)

Version 5.2 (April 2010)

JAPE and JAPE-related

Other Changes

Version 5.1 (December 2009)

New Features

JAPE improvements

Other improvements and bug fixes

Version 5.0 (May 2009)

Major New Features

Other New Features and Improvements

Specific Bug Fixes

Version 4.0 (July 2007)

Major New Features

Other New Features and Improvements

Bug Fixes and Optimizations

Version 3.1 (April 2006)

Major New Features

Other New Features and Improvements

Bug Fixes

January 2005

December 2004

September 2004

Version 3 Beta 1 (August 2004)

July 2004

June 2004

April 2004

March 2004

Version 2.2 – August 2003

Version 2.1 – February 2003

June 2002

Version 5.1 Plugins Name Map

Obsolete CREOLE Plugins

Ontotext JapeC Compiler

Google Plugin

Yahoo Plugin

Using the YahooPR

Gazetteer Visual Resource - GAZE

Display Modes

Linear Definition Pane

Linear Definition Toolbar

Operations on Linear Definition Nodes

Gazetteer List Pane

Mapping Definition Pane

Google Translator PR

Design Notes

Patterns

Components

Model, view, controller

Interfaces

Exception Handling

Ant Tasks for GATE

Declaring the Tasks

The packagegapp task - bundling an application with its dependencies

Introduction

Basic Usage

Handling Non-Plugin Resources

Streamlining your Plugins

Bundling Extra Resources

The expandcreoles Task - Merging Annotation-Driven Config into creole.xml

Named-Entity State Machine Patterns

Main.jape

first.jape

firstname.jape

name.jape

Person

Location

Organization

Ambiguities

Contextual information

name_post.jape

date_pre.jape

date.jape

reldate.jape

number.jape

address.jape

url.jape

identifier.jape

jobtitle.jape

final.jape

unknown.jape

name_context.jape

org_context.jape

loc_context.jape

clean.jape

Part-of-Speech Tags used in the Hepple Tagger

References

Developing Language Processing Components with GATE Version 8 (a User Guide) For GATE version 8.1-snapshot (development builds) (built October 14, 2014) Hamish Cunningham Diana Maynard Kalina Bontcheva Valentin Tablan Niraj Aswani Ian Roberts Genevieve Gorrell Adam Funk Angus Roberts Danica Damljanovic Thomas Heitz Mark A. Greenwood Horacio Saggion Johann Petrak Yaoyong Li Wim Peters et al ©The University of Sheeld, Department of Computer Science 2001-2014 https://gate.ac.uk/ This user manual is free, but please consider making a donation. HTML version: https://gate.ac.uk/userguide Work on GATE has been partly supported by EPSRC grants GR/K25267 (Large-Scale Information Extraction), GR/M31699 (GATE 2), RA007940 (EMILLE), GR/N15764/01 (AKT) and GR/R85150/01 (MIAKT), AHRB grant APN16396 (ETCSL/GATE), Ontotext Matrixware, the Information Retrieval Facility and several EU-funded projects: (TrendMiner, uComp, Arcomem, SEKT, TAO, NeOn, MediaCampaign, Musing, KnowledgeWeb, PrestoSpace, h-TechSight, and enIRaF).

Developing Language Processing Components with GATE Version 8 ©2014 The University of Sheeld, Department of Computer Science The University of Sheeld, Department of Computer Science Regent Court 211 Portobello Sheeld S1 4DP United Kingdom https://gate.ac.uk This work is licenced under the Creative Commons Attribution-No Derivative Licence. You are free to copy, distribute, display, and perform the work under the following conditions: Attribution You must give the original author credit. No Derivative Works You may not alter, transform, or build upon this work. With the understanding that: Waiver Any of the above conditions can be waived if you get permission from the copyright holder. Other Rights In no way are any of the following rights aected by the license: your fair dealing or fair use rights; the author's moral rights; rights other persons may have either in the work itself or in how the work is used, such as publicity or privacy rights. Notice For any reuse or distribution, you must make clear to others the licence terms of this work. For more information about the Creative Commons Attribution-No Derivative License, please visit this web address: http://creativecommons.org/licenses/by-nd/2.0/uk/

Brief Contents I GATE Basics 1 Introduction 2 Installing and Running GATE 3 Using GATE Developer 4 CREOLE: the GATE Component Model 5 Language Resources: Corpora, Documents and Annotations 6 ANNIE: a Nearly-New Information Extraction System II GATE for Advanced Users 7 GATE Embedded 8 JAPE: Regular Expressions over Annotations 9 ANNIC: ANNotations-In-Context 10 Performance Evaluation of Language Analysers 11 Proling Processing Resources 12 Developing GATE III CREOLE Plugins 13 Gazetteers 14 Working with Ontologies 15 Non-English Language Support 16 Domain Specic Resources 17 Tools for Social Media Data 18 Parsers iii 3 5 29 39 71 93 117 137 139 193 233 243 273 281 293 295 317 357 365 373 377

iv 19 Machine Learning 20 Tools for Alignment Tasks 21 Crowdsourcing Data with GATE 22 Combining GATE and UIMA 23 More (CREOLE) Plugins IV The GATE Family: Cloud, MIMIR, Teamware 24 GATE Cloud Contents 391 441 457 469 481 555 557 25 GATE Teamware: A Web-based Collaborative Corpus Annotation Tool 567 26 GATE Mímir Appendices A Change Log B Version 5.1 Plugins Name Map C Obsolete CREOLE Plugins D Design Notes E Ant Tasks for GATE F Named-Entity State Machine Patterns G Part-of-Speech Tags used in the Hepple Tagger References 581 583 583 621 623 631 639 647 655 657

Contents I GATE Basics 1 Introduction 1.1 How to Use this Text . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.2 Context . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.3 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.3.1 Developing and Deploying Language Processing Facilities . . . . . . . 1.3.2 Built-In Components . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.3.3 Additional Facilities in GATE Developer/Embedded . . . . . . . . . . 1.3.4 An Example . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.4 Some Evaluations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.5 Recent Changes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.5.1 Next Release . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.5.2 Version 8.0 (May 2014) . . . . . . . . . . . . . . . . . . . . . . . . . . 1.6 Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 Installing and Running GATE 2.1 Downloading GATE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Installing and Running GATE . . . . . . . . . . . . . . . . . . . . . . . . . . 2.2 2.2.1 The Easy Way . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2.2.2 The Hard Way (1) . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2.2.3 The Hard Way (2): Subversion . . . . . . . . . . . . . . . . . . . . . 2.2.4 Running GATE Developer on Unix/Linux . . . . . . . . . . . . . . . 2.3 Using System Properties with GATE . . . . . . . . . . . . . . . . . . . . . . 2.4 Changing GATE's launch conguration . . . . . . . . . . . . . . . . . . . . . 2.5 Conguring GATE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2.6 Building GATE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2.6.1 Using GATE with Maven/Ivy . . . . . . . . . . . . . . . . . . . . . . 2.7 Uninstalling GATE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2.8 Troubleshooting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 Using GATE Developer 3.1 The GATE Developer Main Window . . . . . . . . . . . . . . . . . . . . . . 3.2 Loading and Viewing Documents . . . . . . . . . . . . . . . . . . . . . . . . 3.3 Creating and Viewing Corpora . . . . . . . . . . . . . . . . . . . . . . . . . . v 3 5 8 8 9 9 11 12 12 14 15 15 16 19 29 29 29 29 29 31 31 32 34 35 36 37 38 38 39 40 42 45

vi Contents Installing and updating CREOLE Plugins 3.4 Working with Annotations . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3.4.1 The Annotation Sets View . . . . . . . . . . . . . . . . . . . . . . . . 3.4.2 The Annotations List View . . . . . . . . . . . . . . . . . . . . . . . 3.4.3 The Annotations Stack View . . . . . . . . . . . . . . . . . . . . . . . 3.4.4 The Co-reference Editor . . . . . . . . . . . . . . . . . . . . . . . . . 3.4.5 Creating and Editing Annotations . . . . . . . . . . . . . . . . . . . . 3.4.6 Schema-Driven Editing . . . . . . . . . . . . . . . . . . . . . . . . . . 3.4.7 Printing Text with Annotations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3.5 Using CREOLE Plugins . . . . . . . . . . . . . . . . . . . 3.6 3.7 Loading and Using Processing Resources . . . . . . . . . . . . . . . . . . . . 3.8 Creating and Running an Application . . . . . . . . . . . . . . . . . . . . . . 3.8.1 Running an Application on a Datastore . . . . . . . . . . . . . . . . . 3.8.2 Running PRs Conditionally on Document Features . . . . . . . . . . 3.8.3 Doing Information Extraction with ANNIE . . . . . . . . . . . . . . . 3.8.4 Modifying ANNIE . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3.9 Saving Applications and Language Resources . . . . . . . . . . . . . . . . . . Saving Documents to File . . . . . . . . . . . . . . . . . . . . . . . . Saving and Restoring LRs in Datastores . . . . . . . . . . . . . . . . Saving Application States to a File . . . . . . . . . . . . . . . . . . . Saving an Application with its Resources (e.g. GATECloud.net) . . . 3.10 Keyboard Shortcuts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3.11 Miscellaneous . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3.11.1 Stopping GATE from Restoring Developer Sessions/Options . . . . . 3.11.2 Working with Unicode . . . . . . . . . . . . . . . . . . . . . . . . . . 3.9.1 3.9.2 3.9.3 3.9.4 4 CREOLE: the GATE Component Model 4.1 The Web and CREOLE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4.2 The GATE Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4.3 The Lifecycle of a CREOLE Resource . . . . . . . . . . . . . . . . . . . . . . 4.4 Processing Resources and Applications . . . . . . . . . . . . . . . . . . . . . 4.5 Language Resources and Datastores . . . . . . . . . . . . . . . . . . . . . . . 4.6 Built-in CREOLE Resources . . . . . . . . . . . . . . . . . . . . . . . . . . . 4.7 CREOLE Resource Conguration . . . . . . . . . . . . . . . . . . . . . . . . 4.7.1 Conguration with XML . . . . . . . . . . . . . . . . . . . . . . . . . 4.7.2 Conguring Resources using Annotations . . . . . . . . . . . . . . . . 4.7.3 Mixing the Conguration Styles . . . . . . . . . . . . . . . . . . . . . 4.7.4 Loading Third-Party Libraries using Apache Ivy . . . . . . . . . . . . 4.8 Tools: How to Add Utilities to GATE Developer . . . . . . . . . . . . . . . . 4.8.1 Putting Your Tools in a Sub-Menu . . . . . . . . . . . . . . . . . . . 4.8.2 Adding Tools To Existing Resource Types . . . . . . . . . . . . . . . 5 Language Resources: Corpora, Documents and Annotations 5.1 Features: Simple Attribute/Value Data . . . . . . . . . . . . . . . . . . . . . 47 47 48 48 49 50 53 54 55 57 58 60 60 61 62 62 63 63 64 65 66 67 69 69 70 71 72 73 73 74 75 75 76 77 82 87 89 90 91 91 93 93

Contents vii 5.2 Corpora: Sets of Documents plus Features . . . . . . . . . . . . . . . . . . . 5.3 Documents: Content plus Annotations plus Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5.4 Annotations: Directed Acyclic Graphs 5.4.1 Annotation Schemas . . . . . . . . . . . . . . . . . . . . . . . . . . . 5.4.2 Examples of Annotated Documents . . . . . . . . . . . . . . . . . . . 5.4.3 Creating, Viewing and Editing Diverse Annotation Types . . . . . . . 5.5 Document Formats . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 94 94 94 96 99 99 5.5.1 Detecting the Right Reader . . . . . . . . . . . . . . . . . . . . . . . 101 5.5.2 XML . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 102 5.5.3 HTML . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 110 5.5.4 SGML . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111 5.5.5 Plain text . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111 5.5.6 RTF . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113 5.5.7 Email 5.5.8 PDF Files and Oce Documents . . . . . . . . . . . . . . . . . . . . 114 5.5.9 UIMA CAS Documents . . . . . . . . . . . . . . . . . . . . . . . . . 114 5.5.10 CoNLL/IOB Documents . . . . . . . . . . . . . . . . . . . . . . . . . 115 5.6 XML Input/Output . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 116 6 ANNIE: a Nearly-New Information Extraction System 117 6.1 Document Reset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 118 6.2 Tokeniser . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 119 6.2.1 Tokeniser Rules . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 119 6.2.2 Token Types . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120 6.2.3 English Tokeniser . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 121 6.3 Gazetteer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 121 6.4 Sentence Splitter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 123 6.5 RegEx Sentence Splitter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 124 6.6 Part of Speech Tagger . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 125 6.7 Semantic Tagger . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 126 6.8 Orthographic Coreference (OrthoMatcher) . . . . . . . . . . . . . . . . . . . 127 6.8.1 GATE Interface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 127 6.8.2 Resources . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128 6.8.3 Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128 6.9.1 Quoted Speech Submodule . . . . . . . . . . . . . . . . . . . . . . . . 129 6.9.2 Pleonastic It Submodule . . . . . . . . . . . . . . . . . . . . . . . . . 129 6.9.3 Pronominal Resolution Submodule . . . . . . . . . . . . . . . . . . . 129 6.9.4 Detailed Description of the Algorithm . . . . . . . . . . . . . . . . . . 130 6.10 A Walk-Through Example . . . . . . . . . . . . . . . . . . . . . . . . . . . . 134 6.10.1 Step 1 - Tokenisation . . . . . . . . . . . . . . . . . . . . . . . . . . . 134 6.10.2 Step 2 - List Lookup . . . . . . . . . . . . . . . . . . . . . . . . . . . 135 6.10.3 Step 3 - Grammar Rules . . . . . . . . . . . . . . . . . . . . . . . . . 135 6.9 Pronominal Coreference

viii II GATE for Advanced Users Contents 137 7 GATE Embedded 7.8.1 139 7.1 Quick Start with GATE Embedded . . . . . . . . . . . . . . . . . . . . . . . 139 7.2 Resource Management in GATE Embedded . . . . . . . . . . . . . . . . . . 140 7.3 Using CREOLE Plugins . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 143 7.4 Language Resources . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 145 7.4.1 GATE Documents . . . . . . . . . . . . . . . . . . . . . . . . . . . . 145 7.4.2 Feature Maps . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 145 7.4.3 Annotation Sets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 147 7.4.4 Annotations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148 7.4.5 GATE Corpora . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 150 7.5 Processing Resources . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 152 7.6 Controllers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 152 7.7 Modelling Relations between Annotations . . . . . . . . . . . . . . . . . . . 155 7.8 Duplicating a Resource . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 157 Sharable properties . . . . . . . . . . . . . . . . . . . . . . . . . . . . 158 7.9 Persistent Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 159 7.10 Ontologies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 160 7.11 Creating a New Annotation Schema . . . . . . . . . . . . . . . . . . . . . . . 161 7.12 Creating a New CREOLE Resource . . . . . . . . . . . . . . . . . . . . . . . 162 7.13 Adding Support for a New Document Format . . . . . . . . . . . . . . . . . 165 7.14 Using GATE Embedded in a Multithreaded Environment . . . . . . . . . . . 167 7.15 Using GATE Embedded within a Spring Application . . . . . . . . . . . . . 168 7.15.1 Duplication in Spring . . . . . . . . . . . . . . . . . . . . . . . . . . . 171 7.15.2 Spring pooling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 172 7.15.3 Further reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 174 7.16 Using GATE Embedded within a Tomcat Web Application . . . . . . . . . . 174 7.16.1 Recommended Directory Structure . . . . . . . . . . . . . . . . . . . 174 7.16.2 Conguration Files . . . . . . . . . . . . . . . . . . . . . . . . . . . . 175 7.16.3 Initialization Code . . . . . . . . . . . . . . . . . . . . . . . . . . . . 175 7.17 Groovy for GATE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 176 7.17.1 Groovy Scripting Console for GATE . . . . . . . . . . . . . . . . . . 177 7.17.2 Groovy scripting PR . . . . . . . . . . . . . . . . . . . . . . . . . . . 178 7.17.3 The Scriptable Controller . . . . . . . . . . . . . . . . . . . . . . . . 181 7.17.4 Utility methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 188 . . . . . . . . . . . . . . . . . . . . . . . . . 189 7.18 Saving Cong Data to gate.xml 7.19 Annotation merging through the API . . . . . . . . . . . . . . . . . . . . . . 189 7.20 Using Resource Helpers to Extend the API . . . . . . . . . . . . . . . . . . . 190 8 JAPE: Regular Expressions over Annotations 193 8.1 The Left-Hand Side . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 195 8.1.1 Matching Entire Annotation Types . . . . . . . . . . . . . . . . . . . 195 8.1.2 Using Features and Values . . . . . . . . . . . . . . . . . . . . . . . . 196

分享到：

赞收藏

资料库

GATE 8 使用指南.pdf

相关推荐

人工智能

热门标签

最新资料