Natural Language ProcessingTuring’s PredictionWas Turing Right?Another Application - MTMT - The LimitsSlide 6Going Both WaysWhen Meaning is CriticalJavaJava, ContinuedIt’s All about MappingWhat Are We Going to Map to?English: What is the average rainfall, in Austin, in months with 30 days?Designing a Mapping Function for NL UnderstandingAmbiguity – the Core ProblemMorphological Analysis and POS TaggingSlide 17Slide 18Morphological Analysis Using a Finite State TransducerStochastic POS TaggingParsing - Building a TreeWhy Cats PaintWhy Paint CatsThe Importance of Parsing Even When We’re Not Doing Full UnderstandingGrammar RulesThe Lexicon is ImportantParsing: Dealing with AmbiguityUsing Domain KnowledgeA Harder OneHow Bad is the Ambiguity?Parsing: GappingSemantics: The Meaning of WordsSemantics: The Meaning of PhrasesBut What About This One?And Another OneIdioms Don’t Work This WayPutting Phrases TogetherLanguage at its Most Straightforward – Propositional ContentWhen There’s More - PresuppositionsWhen There’s More – (Shared?) PresuppositionsCoherenceWe Can’t Say it AllConversational PostulatesConversational Postulates and Scalar ImplicatureAnother Example of Scalar ImplicatureWhen There’s More – Conversational Postulates and InferenceSlide 47Slide 48Slide 49When There’s More – Conversational Postulates and Illocutionary ForceSlide 51Slide 52Slide 53Slide 54Sometimes it is Very SubtleWhat About Applications Where Almost is OK?Going the Other Way: GenerationSlide 58One Problem - What is Reusable?Spoken Language - UnderstandingSpoken Language - GenerationA Recent Loebner Prize WinnerNatural Language ProcessingR & N 22Turing’s Prediction1950 Turing predicted that in about fifty years "an average interrogator will not have more than a 70 percent chance of making the right identification after five minutes of questioning".Was Turing Right?>What's the best place to eat Chinese food? ALICE: My favorite places are California and Maine. Holland is cool too.>What do you like about Maine? ALICE: The special effects are the best.Another Application - MTAustin Police are trying to find the person responsible for robbing a bank in Downtown Austin. El policía de Austin está intentando encontrar a la persona responsable de robar un banco en Austin céntrica.The police of Austin is trying to find the responsible person to rob a bank in centric Austin.MT - The LimitsA Florida teen charged with hiring an undercover policeman to shoot and kill his mother instructed the purported hitman not to damage the family television during the attack, police said on Thursday.Un adolescente de la Florida cargado con emplear a un policía de la cubierta interior para tirar y para matar a su madre mandó a hitman pretendida para no dañar la televisión de la familia durante el ataque, limpia dicho el jueves. An adolescent of Florida loaded with using a police of the inner cover to throw and to kill his mother commanded to hitman tried not to damage the television of the family during the attack, clean said Thursday.MT - The LimitsI have a dream, that my four little children will one day live in a nation where they will not be judged by the color of their skin but by the content of their character. I have a dream today – Martin Luther KingI am a sleepy, that my four small children a day of alive in a nation in where they will not be judged by the color of its skin but by the content of its character. I am a sleepy today. (Spanish)http://www.shtick.org/Translation/translation47.htmGoing Both WaysNotice that both of these applications require that we process language in two directions:•Understanding•GenerationBut also notice that it is possible to do a somewhat passable job without going through any meaning representation.When Meaning is CriticalEnglish: Put the kid’s cereal on the bottom shelves.Javaimport java.util.ArrayList;public class GroceryStore{ private int[][][] shelves; private ArrayList products; public void placeProducts(String productFile) { FileReader r = new FileReader(productFile); GroceryItemFactory factory = new GroceryItemFactory(); while(r.hasNext()) products.add( factory.createItem(r.readNext())); ThreeDLoc startLoc; GroceryItem temp; for(itemNum = 0; itemNum < products.size(); itemNum++) { temp = (GroceryItem)(products.get(itemNum)) startLoc = temp.getPlacement(this); shelves[startLoc.getX()][startLoc.getY()][startLoc.getY()]= tempgetIDNum(); } }}Java, Continuedpublic class ChildrensCereal extends GroceryItem{ private static final int PREFERRED_X = -1; private static final int PREFERRED_Y = 0; private static final int PREFERRED_Z = 0; public ThreeDLoc getPlacement(GroceryStore store) { ThreeDLoc result = new ThreeDLoc(); result.setX(store.find(this)); result.setY(PREFERRED_Y); result.setZ(PREFERRED_Z); return result; }}It’s All about MappingWhat Are We Going to Map to?English: Do you know how much it rains in Austin?MonthsMonthDaysThe database:RainfallByStationyearmonthstationrainfallStationsstationCityEnglish: What is the average rainfall, in Austin, in months with 30 days?SQL: SELECT Avg(RainfallByStation.rainfall) AS AvgOfrainfall FROM Stations INNER JOIN (Months INNER JOIN RainfallByStation ON Months.Month = RainfallByStation.month) ON Stations.station = RainfallByStation.stationHAVING (((Stations.City)="Austin") AND ((Months.Days)=30));Designing a Mapping Function for NL Understanding•Morphological Analysis and POS tagging* The womans goed home.•Syntactic Analysis (Parsing)* Fishing went boys older•Extracting MeaningColorless green ideas sleep furiously.Sue cooked. The potatoes cooked. * Sue and the potatoes cooked.•Putting it All in ContextMy cat saw a bird out the window. It batted at it.•What isn’t saidWinnie doesn’t like August. He doesn’t like melted ice cream.Ambiguity – the Core Problem•Time flies like an arrow.•Fruit flies like a banana.•I hit the boy with the blue shirt (a bat). •I saw the Grand Canyon (a Boeing 747) flying to New York.•I know more beautiful women than Kylie.•I only want potatoes or rice and beans.•The boys may not come.•Is there water in the fridge?•Who cares?•Have you finished writing your paper? I’ve written the outline.Morphological Analysis and POS TaggingMorphological Analysis:played = play + ed = play (V) + PASTsaw = see (V) + PASTleaves =Morphological Analysis