Semantics and Semantic AnalysisMeaningMeaning, contSemanticsSo What IS Meaning?ExampleExample, continuedKnowledge Representation for NLPStructured Knowledge RepresentationsBasics of Associative NetworksSemantic NetsSemantic Net ExamplesGeneric/IndividualIndividuation exampleFramesSimple Frame ExampleUsage of FramesScriptsRestaurant Script ExampleRestaurant ScriptComments on ScriptsFirst Order Predicate Calculus (FOPC)FOPC SemanticsVariables and QuantifiersFOPC ExamplesChoosing a RepresentationVerifiabilityUnambiguous RepresentationAmbiguity and VaguenessRepresenting Similar ConceptsCanonical FormHow to Produce a Canonical FormInferenceNon-Yes/No QuestionsMeaning Structure of LanguageCompositional SemanticsSyntax-Driven SemanticsSpecific vs. General-Purpose RulesSemantic AttachmentsA Simple ExampleSlide 41Doing Compositional SemanticsWhat do we do with them?Option 1 (Integrated Semantic Analysis)Option 2: Post-hoc Semantic AnalysisCompositional Semantics SummaryNon-Compositional LanguageFeature and Information ExtractionFeature ExtractionSlide 50Information ExtractionSome Examples of Information ExtractionSlide 53Staged ApproachCascaded ProcessNamed EntitiesComplex Entities and RelationshipsWhy Does This Work?SummaryCSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari1Some slides adapted from Dorr, www.umiacs.umd.edu/~christof/courses/cmsc723-fall04 , Kurfess: www.csc.calpoly.edu/~fkurfess/Courses/CSC-481/W03/Slides/3-Knowledge-Representation.ppt and Hirschberg: www1.cs.columbia.edu/~julia/cs4705/syllabus.htmlSemantics and Semantic AnalysisCSC 9010: Special Topics. Natural Language Processing.Paula Matuszek, Mary-Angela PapalaskariSpring, 2005CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari2Some slides adapted from Dorr, www.umiacs.umd.edu/~christof/courses/cmsc723-fall04 , Kurfess: www.csc.calpoly.edu/~fkurfess/Courses/CSC-481/W03/Slides/3-Knowledge-Representation.ppt and Hirschberg: www1.cs.columbia.edu/~julia/cs4705/syllabus.htmlMeaning•So far, we have focused on the structure of language, not on what things mean•We have been doing natural language processing, but not natural language understanding.•So what is natural language understanding?–Answering an essay question on an exam?–Deciding what to order at a restaurant by reading a menu?–Realizing you’ve been insulted?–Appreciating a sonnet?•As hard as answering "What is artificial intelligence?"CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari3Some slides adapted from Dorr, www.umiacs.umd.edu/~christof/courses/cmsc723-fall04 , Kurfess: www.csc.calpoly.edu/~fkurfess/Courses/CSC-481/W03/Slides/3-Knowledge-Representation.ppt and Hirschberg: www1.cs.columbia.edu/~julia/cs4705/syllabus.htmlMeaning, cont•On the practical side, we want to “understand” natural language because morphology- and syntax-based methods will only take us so far in some things:–Machine translation–Generation–Question answering•So we saw how we could use n-grams to choose the more likely translation for a word given other words. But n-grams can’t give us the potential translations in the first place.CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari4Some slides adapted from Dorr, www.umiacs.umd.edu/~christof/courses/cmsc723-fall04 , Kurfess: www.csc.calpoly.edu/~fkurfess/Courses/CSC-481/W03/Slides/3-Knowledge-Representation.ppt and Hirschberg: www1.cs.columbia.edu/~julia/cs4705/syllabus.htmlSemantics•What kinds of things can we not do well with the tools we have already looked at?–Retrieve information in response to unconstrained questions: e.g., travel planning–Accurate translations–Play the "chooser" side of 20 Questions–Read a newspaper article and answer questions about it•These tasks require that we also consider semantics: the meaning of our tokens and their sequencesCSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari5Some slides adapted from Dorr, www.umiacs.umd.edu/~christof/courses/cmsc723-fall04 , Kurfess: www.csc.calpoly.edu/~fkurfess/Courses/CSC-481/W03/Slides/3-Knowledge-Representation.ppt and Hirschberg: www1.cs.columbia.edu/~julia/cs4705/syllabus.htmlSo What IS Meaning?•From NLP viewpoint, meaning is a mapping from linguistic forms to some kind of representation of knowledge of the world•It is interpreted within the framework of some sort of action to be taken. •Often we manipulate symbols all the way through; the “meaning” is put in by the human user. Translations, for instance.•But not always – voice command systems, for instance, may map from the representation into actions.CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari6Some slides adapted from Dorr, www.umiacs.umd.edu/~christof/courses/cmsc723-fall04 , Kurfess: www.csc.calpoly.edu/~fkurfess/Courses/CSC-481/W03/Slides/3-Knowledge-Representation.ppt and Hirschberg: www1.cs.columbia.edu/~julia/cs4705/syllabus.htmlExample•Question: Is there a restaurant in King of Prussia serving vegetarian dinners?•From a restaurant database–Lemon Grass is a sister restaurant to the one in West Philadelphia serving traditional Thai dishes in addition to a complete vegetarian Thai menu. The service and atmosphere are quite pleasant. A welcome addition to the King of Prussia area.•What do we need to know to answer this question from this text?•Can we unambiguously answer it?CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari7Some slides adapted from Dorr, www.umiacs.umd.edu/~christof/courses/cmsc723-fall04 , Kurfess: www.csc.calpoly.edu/~fkurfess/Courses/CSC-481/W03/Slides/3-Knowledge-Representation.ppt and Hirschberg: www1.cs.columbia.edu/~julia/cs4705/syllabus.htmlExample, continued•Is there a restaurant in King of Prussia serving vegetarian dinners? Yes.•Lemon Grass is a sister restaurant to the one in West Philadelphia serving traditional Thai dishes in addition to a complete vegetarian Thai menu. The service and atmosphere are quite pleasant. A welcome addition to the King of Prussia area.•What do we need to know? –Vegetarian Thai menu = vegetarian dinners–Welcome addition to the KoP area = in KoP•Can we unambiguously answer it?–No. But we can be fairly certain.•The only