An Introduction to NLG What is Natural Language Generation? Some Example Systems Types of NLG Applications When are NLG Techniques Appropriate? NLG System.

Slides:



Advertisements
Similar presentations
Natural Language Generation
Advertisements

Effective Searching Strategies and Techniques
A very short introduction to Natural Language Generation Kees van Deemter Computing Science University of Aberdeen.
Map of Human Computer Interaction
Chapter 5: Introduction to Information Retrieval
December 2003CSA3050: Natural Language Generation 1 What is Natural Language Generation? When is NLG an Appropriate Technology? NLG System Architectures.
IEC Substation Configuration Language and Its Impact on the Engineering of Distribution Substation Systems Notes Dr. Alexander Apostolov.
Natural Language Generation: Discourse Planning
Natural Language Generation Research Presentation Presenter Shamima Mithun.
A Pipelined Architecture Document Planning Microplanning Surface Realisation Document Plan Text Specification.
Search Engines and Information Retrieval
IR & Metadata. Metadata Didn’t we already talk about this? We discussed what metadata is and its types –Data about data –Descriptive metadata is external.
A Flexible Workbench for Document Analysis and Text Mining NLDB’2004, Salford, June Gulla, Brasethvik and Kaada A Flexible Workbench for Document.
 Manmatha MetaSearch R. Manmatha, Center for Intelligent Information Retrieval, Computer Science Department, University of Massachusetts, Amherst.
1 CS 430 / INFO 430 Information Retrieval Lecture 24 Usability 2.
ReQuest (Validating Semantic Searches) Norman Piedade de Noronha 16 th July, 2004.
Creating Architectural Descriptions. Outline Standardizing architectural descriptions: The IEEE has published, “Recommended Practice for Architectural.
Natural Language Generation Ling 571 Fei Xia Week 8: 11/17/05.
Claim Tracking System. Why was the Claim Tracking System Built? Mandated by the 2002 Legislature Automated Monthly Summary Reports Track and Ensure Construction.
Software Development, Programming, Testing & Implementation.
MSF Testing Introduction Functional Testing Performance Testing.
CAREERS IN LINGUISTICS OUTSIDE OF ACADEMIA CAREERS IN INDUSTRY.
Data Analysis for Evaluation Eric Graig, Ph.D.. Slide 2 Innovation Network, Inc. Purpose of this Training To increase your skills in analysis and interpretation.
Before I stated the database I had to save it into My Documents> ICT> You can do it> D201EPORTFOLIO> Evidence For the field group food item, I set the.
TESTING STRATEGY Requires a focus because there are many possible test areas and different types of testing available for each one of those areas. Because.
Chapter 6 System Engineering - Computer-based system - System engineering process - “Business process” engineering - Product engineering (Source: Pressman,
Search Engines and Information Retrieval Chapter 1.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
CQRS User Story – SERVICE PROVIDER Chris Brown – project manager 05 September 2012 Calculating Quality Reporting Service.
Chapter 8 Architecture Analysis. 8 – Architecture Analysis 8.1 Analysis Techniques 8.2 Quantitative Analysis  Performance Views  Performance.
Software Engineering 2003 Jyrki Nummenmaa 1 CASE Tools CASE = Computer-Aided Software Engineering A set of tools to (optimally) assist in each.
Multi-agent Research Tool (MART) A proposal for MSE project Madhukar Kumar.
Knowledge-rich approaches for text summarization Minna Vasankari
 Maintains the Instrument Database  Generates the Calibration Schedules  Maintains Calibration Records  Provides Facility to enter All types of.
Tunis International Centre for Environmental Technologies Small Seminar on Networking Technology Information Centers UNFCCC secretariat offices Bonn, Germany.
Computing Fundamentals Module Lesson 19 — Using Technology to Solve Problems Computer Literacy BASICS.
Generalizable Element Namespace Model Element name visibility isSpecification Classifier isRoot Constraint Body Use Cases CS/SWE 421 Introduction to Software.
Example 1: FoG Goldberg et al 1994 Input: Numerical weather forecast over a given time period Output: textual description of predicted weather. User: Environment.
Examining data using Microsoft Access Queries Using Criteria and Calculations SESSION 3.2 This section covers specifying an exact match condition in a.
Module 5: Data Collection. This training session contains information regarding: Audit Cycle Begins Audit Cycle Begins Questionnaire Administration Questionnaire.
1 Enviromatics Environmental sampling Environmental sampling Вонр. проф. д-р Александар Маркоски Технички факултет – Битола 2008 год.
Evaluation of Agent Building Tools and Implementation of a Prototype for Information Gathering Leif M. Koch University of Waterloo August 2001.
ESD.70J Engineering Economy Module - Session 21 ESD.70J Engineering Economy Fall 2009 Session Two Michel-Alexandre Cardin – Prof. Richard.
Introduction to Computational Linguistics
The Measurement of Nonmarket Sector Outputs and Inputs Using Cost Weights 2008 World Congress on National Accounts and Economic Performance Measures for.
1 Welcome : To the third learning sequence “ DB ACTORS “ Present learning: We shall explore the following topics: - DB limitations. - DB actors. - DB Administrator.
Computing Fundamentals Module Lesson 6 — Using Technology to Solve Problems Computer Literacy BASICS.
Human Computer Interaction
INFORMATION MANAGEMENT Module INFORMATION MANAGEMENT Module
The steps involved in developing an Information System are: Analysis Feasibility Study System Design Testing Implementation Documentation.
Jette Viethen 20 April 2007NLGeval07 Automatic Evaluation of Referring Expression Generation is Possible.
Web Design and Development. World Wide Web  World Wide Web (WWW or W3), collection of globally distributed text and multimedia documents and files 
Lesson 13 Databases Unit 2—Using the Computer. Computer Concepts BASICS - 22 Objectives Define the purpose and function of database software. Identify.
NLP. Introduction to NLP (U)nderstanding and (G)eneration Language Computer (U) Language (G)
HOW TO SEARCH …………………. By Mamoun Al Rahhal. How to Search Before you start a search operation. Optional selections. Function buttons. Filling Criteria.
Requirements Engineering Requirements Management Lecture-25.
Of An Expert System.  Introduction  What is AI?  Intelligent in Human & Machine? What is Expert System? How are Expert System used? Elements of ES.
Lesson 10—Networking BASICS1 Networking BASICS The Internet and Its Tools Unit 3 Lesson 10.
Bringing Order to the Web : Automatically Categorizing Search Results Advisor : Dr. Hsu Graduate : Keng-Wei Chang Author : Hao Chen Susan Dumais.
1 CSC160 Chapter 1: Introduction to JavaScript Chapter 2: Placing JavaScript in an HTML File.
Prepared by: Arjaa Salem Makkawi ID: Sec : 2.
INTRODUCTION TO APPLIED LINGUISTICS
1 Environmental and Disposal Liabilities Intranet Reporting System March 2006 Training Guide.
Ehud Reiter, Computing Science, University of Aberdeen1 CS5545: Natural Language Generation Background Reading: Reiter and Dale, Building Natural Language.
Learning Usage of English KWICly with WebLEAP/DSR
Making Connections: guidance on non-exam assessment
DESIGN MODEL: USE-CASE REALIZATIONS WITH GRASP PATTERNS
KNOWLEDGE ACQUISITION
Intro to Expert Systems Paula Matuszek CSC 8750, Fall, 2004
Computer Literacy BASICS
Presentation transcript:

An Introduction to NLG What is Natural Language Generation? Some Example Systems Types of NLG Applications When are NLG Techniques Appropriate? NLG System Architecture

What is NLG? Natural language generation is the process of deliberately constructing a natural language text in order to meet specified communicative goals. [McDonald 1992]

What is NLG? Goal: –computer software which produces understandable and appropriate texts in English or other human languages Input: –some underlying non-linguistic representation of information Output: –documents, reports, explanations, help messages, and other kinds of texts Knowledge sources required: –knowledge of language and of the domain

Text Language Technology Natural Language Understanding Natural Language Generation Speech Recognition Speech Synthesis Text Meaning Speech

Example System #1: FoG Function: –Produces textual weather reports in English and French Input: –Graphical/numerical weather depiction User: –Environment Canada (Canadian Weather Service) Developer: –CoGenTex Status: –Fielded, in operational use since 1992

FoG: Input

FoG: Output

Example System #2: PlanDoc Function: –Produces a report describing the simulation options that an engineer has explored Input: –A simulation log file User: –Southwestern Bell Developer: –Bellcore and Columbia University Status: –Fielded, in operational use since 1996

PlanDoc: Input RUNID fiberall FIBER 6/19/93 act yes FA FA FA FA ANF co ANF ANF END

PlanDoc: Output This saved fiber refinement includes all DLC changes in Run-ID ALLDLC. RUN-ID FIBERALL demanded that PLAN activate fiber for CSAs 1201, 1301, 1401 and 1501 in 1995 Q2. It requested the placement of a 48-fiber cable from the CO to section 1103 and the placement of 24-fiber cables from section 1201 to section 1301 and from section 1401 to section 1501 in the second quarter of For this refinement, the resulting 20 year route PWE was $856.00K, a $64.11K savings over the BASE plan and the resulting 5 year IFC was $670.20K, a $60.55K savings over the BASE plan.

PEBA-II

University of Edinburgh ILEX System startup page Automatic webpage generation from an annotated data base

PROJECTREPORTER

Example System #3: STOP Function: –Produces a personalised smoking-cessation leaflet Input: –Questionnaire about smoking attitudes, beliefs, history User: –NHS (British Health Service) Developer: –University of Aberdeen Status: –Undergoing clinical evaluation to determine its effectiveness

STOP: Input

STOP: Output Dear Ms Cameron Thank you for taking the trouble to return the smoking questionnaire that we sent you. It appears from your answers that although you're not planning to stop smoking in the near future, you would like to stop if it was easy. You think it would be difficult to stop because smoking helps you cope with stress, it is something to do when you are bored, and smoking stops you putting on weight. However, you have reasons to be confident of success if you did try to stop, and there are ways of coping with the difficulties.

STOP Personalized giving-up smoking advice letters...

Example System #4: TEMSIS Function: –Summarises pollutant information for environmental officials Input: –Environmental data + a specific query User: –Regional environmental agencies in France and Germany Developer: –DFKI GmbH Status: –Prototype developed; requirements for fielded system being analysed

TEMSIS: Input Query ((LANGUAGE FRENCH) (GRENZWERTLAND GERMANY) (BESTAETIGE-MS T) (BESTAETIGE-SS T) (MESSSTATION \"Voelklingen City\") (DB-ID \"#2083\") (SCHADSTOFF \"#19\") (ART MAXIMUM) (ZEIT ((JAHR 1998) (MONAT 7) (TAG 21))))

TEMSIS: Output Summary Le 21/7/1998 à la station de mesure de Völklingen -City, la valeur moyenne maximale d'une demi-heure (Halbstundenmittelwert) pour l'ozone atteignait µg/m³. Par conséquent, selon le decret MIK (MIK- Verordnung), la valeur limite autorisée de 120 µg/m³ n'a pas été dépassée. Der höchste Halbstundenmittelwert für Ozon an der Meßstation Völklingen -City erreichte am µg/m³, womit der gesetzlich zulässige Grenzwert nach MIK-Verordnung von 120 µg/m³ nicht überschritten wurde.

TEMSIS

Types of NLG Applications Automated document production –weather forecasts, simulation reports, letters,... Presentation of information to people in an understandable fashion –medical records, expert system reasoning,... Teaching –information for students in CAL systems Entertainment –jokes (?), stories (??), poetry (???)

The Computer’s Role Two possibilities: #1 The system produces a document without human help: weather forecasts, simulation reports, patient letters summaries of statistical data, explanations of expert system reasoning, context-sensitive help, … #2 The system helps a human author create a document: weather forecasts, simulation reports, patient letters customer-service letters, patent claims, technical documents, job descriptions,...

When are NLG Techniques Appropriate? Options to consider: Text vs Graphics –Which medium is better? Computer generation vs Human authoring –Is the necessary source data available? –Is automation economically justified? NLG vs simple string concatenation –How much variation occurs in output texts? –Are linguistic constraints and optimisations important?

Enforcing Constraints Linguistically well-formed text involves many constraints: –orthography, morphology, syntax –reference, word choice, pragmatics Constraints are automatically enforced in NLG systems –automatic, covers 100% of cases String-concatenation system developers must explicitly enforce constraints by careful design and testing –A lot of work –Hard to guarantee 100% satisfaction

Example: Syntax, aggregation Output of existing Medical AI system: The primary measure you have chosen, CXR shadowing, should be justified in comparison to TLC and walking distance as my data reveals they are better overall. Here are the specific comparisons: TLC has a lower patient cost TLC is more tightly distributed TLC is more objective walking distance has a lower patient cost

Example: Pragmatics Output of system which gives English versions of database queries: –The number of households such that there is at least 1 order with dollar amount greater than or equal to $100. –Humans interpret this as number of “households which have placed an order >= $100” –Actual query returns count of all households in DB if there is any order in the DB (from any household) which is >=$100

A Pipelined Architecture Document Planning Microplanning Surface Realisation Document Plan Text Specification