December 2003CSA3050: Natural Language Generation 1 What is Natural Language Generation? When is NLG an Appropriate Technology? NLG System Architectures.

Slides:



Advertisements
Similar presentations
Chapter 11 user support. Issues –different types of support at different times –implementation and presentation both important –all need careful design.
Advertisements

Programming Paradigms and languages
Software Requirements
Natural Language Generation: Discourse Planning
Chapter 20: Natural Language Generation Presented by: Anastasia Gorbunova LING538: Computational Linguistics, Fall 2006 Speech and Language Processing.
What is NLG? NLG "is the process of deliberately constructing a natural language text in order to meet specified communicative goals". [McDonald 1992]
Natural Language Generation Research Presentation Presenter Shamima Mithun.
Generation Miriam Butt January The Two Sides of Generation 1) Natural Language Generation (NLG) Systems which take information from some database.
Software Requirements
Natural Language Generation Martin Hassel KTH CSC Royal Institute of Technology Stockholm
Software Requirements
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.
1 Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang, Assistant Professor Dept. of Computer Science & Information Engineering National Central.
© De Montfort University, Design Process Howell Istance Department of Computer Science De Montfort University.
Lecture 1 Introduction: Linguistic Theory and Theories
©Ian Sommerville 2000 Software Engineering, 6th edition. Chapter 5 Slide 1 Requirements engineering l The process of establishing the services that the.
Style, Grammar and Punctuation
Artificial Intelligence Research Centre Program Systems Institute Russian Academy of Science Pereslavl-Zalessky Russia.
Basic Concepts The Unified Modeling Language (UML) SYSC System Analysis and Design.
Fundamentals of Python: From First Programs Through Data Structures
Lecture 1, 7/21/2005Natural Language Processing1 CS60057 Speech &Natural Language Processing Autumn 2005 Lecture 1 21 July 2005.
USE Case Model.
Introduction to Natural Language Generation
9/8/20151 Natural Language Processing Lecture Notes 1.
Natural Language Generation An Overview
COMPUTER ASSISTED / AIDED LANGUAGE LEARNING (CALL) By: Sugeili Liliana Chan Santos.
Getting the Language Right ITSW 1410 Presentation Media Software Instructor: Glenda H. Easter.
Natural Language Processing Introduction. 2 Natural Language Processing We’re going to study what goes into getting computers to perform useful and interesting.
THE BIG PICTURE Basic Assumptions Linguistics is the empirical science that studies language (or linguistic behavior) Linguistics proposes theories (models)
Software Requirements Hoang Huu Hanh, Hue University hanh-at-hueuni.edu.vn Lecture 4 & 5.
LOGIC AND ONTOLOGY Both logic and ontology are important areas of philosophy covering large, diverse, and active research projects. These two areas overlap.
INTRODUCTION TO USER DOCUMENTATION Function and purpose Production specifications Evaluate the effectiveness.
Computing Science, University of Aberdeen1 CS4025: Logic-Based Semantics l Compositionality in practice l Producing logic-based meaning representations.
NLP ? Natural Language is one of fundamental aspects of human behaviors. One of the final aim of human-computer communication. Provide easy interaction.
David McDonald BBN Technologies Flexibility counts more than precision.
October 2005CSA3180 NLP1 CSA3180 Natural Language Processing Introduction and Course Overview.
CSA2050 Introduction to Computational Linguistics Lecture 1 Overview.
Introduction to Computational Linguistics
CSA2050 Introduction to Computational Linguistics Lecture 1 What is Computational Linguistics?
Programming Languages and Design Lecture 3 Semantic Specifications of Programming Languages Instructor: Li Ma Department of Computer Science Texas Southern.
L To identify the services that the customer requires from a system and the constraints under which it operates and is developed.
Volgograd State Technical University Applied Computational Linguistic Society Undergraduate and post-graduate scientific researches under the direction.
March 2006Introduction to Computational Linguistics 1 CLINT Tokenisation.
Natural Language Generation Martin Hassel KTH NADA Royal Institute of Technology Stockholm
SYNTAX.
NLP. Introduction to NLP (U)nderstanding and (G)eneration Language Computer (U) Language (G)
Importance of user interface design – Useful, useable, used Three golden rules – Place the user in control – Reduce the user’s memory load – Make the.
CERTIFICATE IV IN BUSINESS JULY 2015 BSBWRT401A - Write Complex Documents.
Requirements Analysis
Software Engineering, COMP201 Slide 1 Software Requirements BY M D ACHARYA Dept of Computer Science.
NATURAL LANGUAGE PROCESSING
Discourse & Natural Language Generation Martin Hassel KTH NADA Royal Institute of Technology Stockholm
Learning Outcome 01 : Be able to design interactive products Unit R005: Creating an interactive product using multimedia components Cambridge Nationals.
Design Evaluation Overview Introduction Model for Interface Design Evaluation Types of Evaluation –Conceptual Design –Usability –Learning Outcome.
1 Software Requirements Descriptions and specifications of a system.
WP4 Models and Contents Quality Assessment
Human Computer Interaction Lecture 21 User Support
REPORT WRITING.
Human Computer Interaction Lecture 21,22 User Support
Writing Requirements Lecture # 23.
Objectives Importance of Requirement Engineering
ENGLISH TEST 45 Minutes – 75 Questions
Software Requirements
Referring Expressions: Definition
Key Linguistic DEVICES Concepts
Chapter 11 user support.
Presentation transcript:

December 2003CSA3050: Natural Language Generation 1 What is Natural Language Generation? When is NLG an Appropriate Technology? NLG System Architectures

December 2003CSA3050: Natural Language Generation 2 Acknowledgements & Resources Ehud Reiter and Robert Dale, Building Natural Language Generation Systems, Cambridge:2000. SIGGEN's resource page Dale & Reiter's ANLP-97 Tutorial on Building Applied Natural Language Generation Systems

December 2003CSA3050: Natural Language Generation 3 Meaning Text Natural Language Understanding Text Natural Language Generation NLP = NLU + NLG

December 2003CSA3050: Natural Language Generation 4 What is NLG? NLG "is the process of deliberately constructing a natural language text in order to meet specified communicative goals". [McDonald 1992] Goal: design of computer software which produces understandable NL utterances. Input: some underlying non-linguistic representation of information Output: documents, reports, explanations, help messages, and other kinds of texts

December 2003CSA3050: Natural Language Generation 5 Why Use NLG? Important information is often stored on computers in ways which are not comprehensible to the end user: NLG systems can present this information to users in an accessible way. When output is so variable that is difficult to capture by means of canned text.

December 2003CSA3050: Natural Language Generation 6 Are NLG and NLU Mirror Images? Both Require Knowledge –knowledge of language –knowledge of the domain Can we use same knowledge to drive NLG and NLU? Reversible grammars

December 2003CSA3050: Natural Language Generation 7 Reversible Grammars are Possible s --> np, vp. np --> n. vp --> v, np. n --> [john]. n --> [mary]. v --> [loves]. v --> [hits].

December 2003CSA3050: Natural Language Generation 8 Reversible Grammar - Output 1 ?- s([john,loves,mary],[]). Yes 2 ?- s(X,[]). X = [john, loves, john] ; X = [john, loves, mary] ; X = [john, hits, john] ; X = [john, hits, mary] ; X = [mary, loves, john] ; X = [mary, loves, mary] ; X = [mary, hits, john] ; X = [mary, hits, mary] ; No

December 2003CSA3050: Natural Language Generation 9 But NLU and NLG Address Fundamentally Different Problems NLU –Management of choices about interpretation. –Handling ill-formed input. NLG –Management of choices about realisation, given that you know what you want to say. –Stylistically appropriate output. –Creating understandable output.

December 2003CSA3050: Natural Language Generation 10 Deciding what to say involves consideration of.... what the content of an utterance should be what information should be omitted; how to organise that content in a coherent discourse; what tone or degree of formality should be adopted; how the material should be broken down into sentences or clauses; what syntactic constructions should be used; how entities should be described; word choice.

December 2003CSA3050: Natural Language Generation 11 Examples of Choices "This course is being taught by Mike Rosner. It is an introduction to natural language generation". lecturers name and course title. style of name two sentences rather than one. passive rather than active for first sentence being taught rather than being given pronoun it in the second sentence

December 2003CSA3050: Natural Language Generation 12 Criteria of Understandability/Quality 1.Clear meaning, good grammar, terminology and sentence structure. 2.Clear meaning but bad grammar, bad terminology, or bad sentence structure. 3.Meaning graspable but ambiguities due to bad terminology or bad sentence structure 4.Meaning unclear but inferrable 5.Meaning absolutely unclear

December 2003CSA3050: Natural Language Generation 13 Examples of Understandability/Quality 1.The US unilaterally reduced China's textile export quotas. 2.US cutted china export ration lonely. 3.A chinese ration US cut it down. 4.Cause states go quotas to reduced. 5.alone cut it up rations alone

December 2003CSA3050: Natural Language Generation 14 When are NLG Techniques Desirable? Necessary source data available in a computationally tractable form. Much variation in output is required. Automation justified on the basis of volume, speed requirements or consistency requirements. Text is the right medium.

December 2003CSA3050: Natural Language Generation 15 Alternatives to/Variations of Natural Language Generation Alternatives –Fixed Templates –Templates with Variables –Graphics. –Manual NLG Variations –Multi-Modal –Dialogue

December 2003CSA3050: Natural Language Generation 16 Choice of Text v. Graphics No hard and fast rules. Examination of existing conventions in a given area of application is useful. Can depend on type of subject matter, e.g. –Information about physical location often better conveyed by graphics. –Information about abstract concepts better conveyed by text. Expertise and language abilities of user.

December 2003CSA3050: Natural Language Generation 17 WIP: Knowledge Based Presentation of Information WIP (Wahlster et al c.1990) Multimodal Presentation system that is able to generate a variety of multimedia documents Input consisting of a formal description of the communicative intent of a planned presentation. generation process is controlled by a set of generation parameters –target group –presentation objective –resource limitation –target language.

December 2003CSA3050: Natural Language Generation 18 Typical Pipelined Architecture Text Planning Sentence Planning Linguistic Realization

December 2003CSA3050: Natural Language Generation 19 Tasks and Architecture in NLG 1.Content determination 2.Discourse planning (≈ paragraphs) 3.Sentence aggregation 4.Lexicalisation 5.Referring expression generation 6.Syntax + morphology 7.Orthographic realization Text Planning Sentence Planning Linguistic Realization

December 2003CSA3050: Natural Language Generation 20 Intermediate Representations Text Planning Sentence Planning Linguistic Realization Text Plan Sentence Plans

December 2003CSA3050: Natural Language Generation 21 1.Content Determination The process of deciding what to say from communicative goals etc. construction of a set of messages from the underlying data source –Messages are aggregations of data that are appropriate for linguistic expression. –Each message may correspond to the meaning of a word or a phrase. –Messages are based on domain entities, concepts, and relations.

December 2003CSA3050: Natural Language Generation 22 Examples of Messages DEPARTURETIME( CALEXPRESS, 1000). ID(NEXTTRAIN, CALEXPRESS) COUNT((TRAIN, SRC(ABERDEEN), DESTINATION(GLASGOW)), 20, PERDAY) The Caledonian Express leaves at 10am The next train is the Caledonian Express There are 20 trains daily from Aberdeen to Glasgow

December 2003CSA3050: Natural Language Generation 23 2.Discourse Planning A text is not just a random collection of sentences The Caledonian Express leaves at 10am. The next train is the Caledonian Express. There are 20 trains daily from Aberdeen to Glasgow Texts have an underlying structure in which the parts are related together The structure can be expressed by means of a text plan

December 2003CSA3050: Natural Language Generation 24 A Text Plan NextTrainInformation IDENTITY(…)DEPARTURETIME(…) COUNT(…) Sequence Elaboration

December 2003CSA3050: Natural Language Generation 25 Text Resulting from Text Plan There are 20 trains daily from Aberdeen to Glasgow. The next train is the Caledonian Express. It leaves Aberdeen at 10am.

December 2003CSA3050: Natural Language Generation Sentence Planning: Aggregation A one-to-one mapping from messages to sentences results in disfluent text Messages need to be combined to produce larger and more complex sentences The result is a sentence specification or SENTENCE PLAN

December 2003CSA3050: Natural Language Generation 27 An Example of Sentence Aggregation Without aggregation: –The next train is the Caledonian Express. It leaves Aberdeen at 10am. With aggregation: –The next train, which leaves at 10am, is the Caledonian Express.

December 2003CSA3050: Natural Language Generation 28 4 Lexicalisation Lexicalisation determines the particular words to be used to express domain concepts and relations In our example, should the DEPARTURETIME relation be expressed using the verb leave or depart ? How do we express different nuances of meaning? What words should be used in different languages?

December 2003CSA3050: Natural Language Generation 29 5Referring Expression Generation Referring expression generation is concerned with how we describe domain entities in such a way that the hearer will know what we are talking about. Choice between –Proper names (type/degree of formality) –Definite Descriptions –Pronouns Major issue is avoiding ambiguity. John hit Bill. He cried out.

December 2003CSA3050: Natural Language Generation 30 6Syntactic and Morphological Realization Morphology: rules of word formation: –walk + ed = walked Syntax: rules of sentence formation –the subject goes before the verb

December 2003CSA3050: Natural Language Generation 31 7 Orthographic Realization Orthographic realization is concerned case, punctuation, typographic issues: font size, column width … sentences begin with upper case letter, end in full stops choice of font other layout issues

December 2003CSA3050: Natural Language Generation 32 Summary NLG is related to NLU but addresses different problems. Quality/understandability is a major issue. NLG is an option when text is an appropriate output medium, and when "mail-merge" style character manipulation is insufficient for the application at hand. Planning considerations enter into the generation of texts. Text generation is a pipeline process involving different representations.