Semantics and Semantic Analysis

1. Semantics and Semantic Analysis CSC 9010: Special Topics. Natural Language Processing. Paula Matuszek, Mary-Angela Papalaskari Spring, 2005 CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

2. Meaning • 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 & Papalaskari

3. Meaning, 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 & Papalaskari

4. Semantics • 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 sequences CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

5. So 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 & Papalaskari

6. Example • 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 & Papalaskari

7. Example, 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 parse that makes sense • Restaurants normally do serve the dinner meal. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

8. Knowledge Representation for NLP • So what representation? • A useful KR needs to give us a way to encode the knowledge relevant to our problem in a way which allows us to use it. Any representation which does this will work. • How do we decide what we want to represent? • Entities, categories, events, time, aspect • Predicates, relationships among entities, arguments (constants, variables) • And…quantifiers, operators (e.g. temporal) • How much structure do we capture? CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

9. Structured Knowledge Representations • Model-based representations reflect the structure of the domain, and then reason based on the model. • Semantic Nets • Frames • Scripts • Sometimes called associative networks CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

10. Basics of Associative Networks • All include • Concepts • Various kinds of links between concepts • “has-part” or aggregation • “is-a” or specialization • More specialized depending on domain • Typically also include • Inheritance • Some kind of procedural attachment CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

11. Semantic Nets • labeled, directed graph • nodes represent objects, concepts, or situations • labels indicate the name • nodes can be instances (individual objects) or classes (generic nodes) • links represent relationships • the relationships contain the structural information of the knowledge to be represented • the label indicates the type of the relationship CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

12. Semantic Net Examples Ship HasA HasA Hull Propulsion Person InstanceOf Instance Instance Steamboat Bob give Mary recipient agent object Candy CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

13. Generic/Individual • Generic describes the idea--the “notion” • static • Individual or instance describes a real entity • must conform to notion of generic • dynamic • “individuate” or “instantiate” • A lot of NLP using semantic nets involves instantiating generic nets based on a given piece of text. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

14. Individuation example Person give Person recipient agent object Thing Generic Representation Process the sentence “Bob gave Mary some candy”. Bob give Mary recipient agent object Candy Instantiation CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

15. Frames • Represent related knowledge about a subject • Frame has a title and a set of slots • Title is what the frame “is” – the concept • Slots capture relationships of the concept to other things • Typically can be organized hierarchically • Most frame systems have an is-a slot • allows the use of inheritance • Slots can contain all kinds of items • Rules, facts, images, video, questions, hypotheses, other frames • In NLP, typically capture relationships to other frames or entities • Slots can also have procedural attachments • on creation, modification, removal of the slot value CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

16. Simple Frame Example CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

17. Usage of Frames • Most operations with frames do one of two things: • Fill slots • Process a piece of text to identify an entity for which we have a frame • Fill as many slots as possible • Use contents of slots • Look up answers to questions • Generate new text CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari [Rogers 1999]

18. Scripts • Describe typical events or sequences • Components are • script variables (players, props) • entry conditions • transactions • exit conditions • Create instance by filling in variables CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

19. Restaurant Script Example • generic template for restaurants • different types • default values • script for a typical sequence of activities at a restaurant • Often has a frame behind it; script is essentially instantiating the frame CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari [Rogers 1999]

20. Restaurant Script EAT-AT-RESTAURANT Script Props: (Restaurant, Money, Food, Menu, Tables, Chairs) Roles: (Hungry-Persons, Wait-Persons, Chef-Persons) Point-of-View: Hungry-Persons Time-of-Occurrence: (Times-of-Operation of Restaurant) Place-of-Occurrence: (Location of Restaurant) Event-Sequence: first: Enter-Restaurant Script then: if (Wait-To-Be-Seated-Sign or Reservations) then Get-Maitre-d's-Attention Script then: Please-Be-Seated Script then: Order-Food-Script then: Eat-Food-Script unless (Long-Wait) when Exit-Restaurant-Angry Script then: if (Food-Quality was better than Palatable) then Compliments-To-The-Chef Script then: Pay-For-It-Script finally: Leave-Restaurant Script [Rogers 1999] CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

21. Comments on Scripts • Obviously takes a lot of time to develop them initially. • The script itself has much of the knowledge • May be serious overkill for most NLP tasks • We need this level of detail if we want to include answers based on reasoning like “Most restaurants do serve dinner.” CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

22. First Order Predicate Calculus (FOPC) • Terms • Constants: Lemon Grass • Functions: LocationOf(Lemon Grass) • Variables: x in LocationOf(x) • Predicates: Relations that hold among objects • Serves(Lemon Grass,VegetarianFood) • Logical Connectives: Permit compositionality of meaning • I only have $5 and I don’t have a lot of time • Have(I,$5) Have(I,LotofTime) CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

23. FOPC Semantics • Sentences in FOPC can be assigned truth values True or False CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

24. Variables and Quantifiers • Existential (): There exists • A restaurant that serves Vegetarian food in KoP • (x) Restaurant(x) Serves(x,VegetarianFoor) Near(LocationOf(x), KoP) • Universal (): For all • All vegetarian restaurants serve vegetarian food • (x) VegetarianRestaurant(x) -> Serves(x,VegetarianFood) CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

25. FOPC Examples • John gave Mary a book • Previously: Give(John,Mary,book) • Better: • (x) Giving(x) Giver(John,x) Givee(Mary,x) Given(book,x) • Full Definition of Give: • (w,x,y,z) Giving(x)  Giver(w,x)  Givee(z,x)  Given(y,x) CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

26. Choosing a Representation • We would like our representation to support: • Verifiability • Unambiguous Representation • Canonical Form • Inference • Expressiveness CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

27. Verifiability • System can match input representation against representations in knowledge base. If it finds a match, it can return Yes; Otherwise No. • Does Lemon Grass serve vegetarian food?Serves(Lemon Grass,vegetarian food) CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

28. Unambiguous Representation • Single linguistic input can have different meaning representations • Each representation unambiguously characterizes one meaning. • Example: small cars and motorcycles are allowed • car(x) & small(x) & motorcycle(y) & small(y) & allowed(x) & allowed(y) • car(x) & small(x) & motorcycle(y) & allowed(x) & allowed(y) CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

29. Ambiguity and Vagueness • An expression is ambiguous if, in a given context, it can be disambiguated to have a specific meaning, from a number of discrete, possible meanings. E.g., bank (financial institution) vs bank (river bank) • An expression is vague, if it refers to a range of a scalar variable, such that, even in a specific context, it’s hard to specify the range entirely. E.g., he’s tall, it’s warm, etc. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

30. Representing Similar Concepts • Distinct inputs could have the same meaning • Does Lemon Grass have vegetarian dishes? • Do they have vegetarian food at Lemon Grass? • Are vegetarian dishes served at Lemon Grass? • Does Lemon Grass serve vegetarian fare? • Alternatives • Four different semantic representations • Store all possible meaning representations in KB CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

31. Canonical Form • Solution: Inputs that mean same thing have same meaning representation • Is this easy? No! • Vegetarian dishes, vegetarian food, vegetarian fare • Have, serve • What to do? CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

32. How to Produce a Canonical Form • Systematic Meaning Representations can be derived from thesaurus • food ___ • dish ___|____one overlapping meaning sense • fare ___| • We can systematically relate syntactic constructions • [S [NP Lemon Grass] serves [NP vegetarian dishes]] • [S [NP vegetarian dishes] are served at [NP Lemon Grass]] CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

33. Inference • Consider a more complex request • Can vegetarians eat at Lemon Grass? • Vs: Does Lemon Grass serve vegetarian food? • Why do these result in the same answer? • Inference: Draw conclusions about truth of propositions not explicitly stored in KB • serve(Lemon Grass,VegetarianFood) => CanEat(Vegetarians,At Lemon Grass) CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

34. Non-Yes/No Questions • Example: I'd like to find a restaurant where I can get vegetarian food. • serve(x,VegetarianFood) • Matching succeeds only if variable x can be replaced by known object in KB. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

35. Meaning Structure of Language • Human Languages • Display a basic predicate-argument structure • Make use of variables • Make use of quantifiers • Display a partially compositional semantics CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

36. Compositional Semantics • Assumption: The meaning of the whole is comprised of the meaning of its parts • George cooks. Dan eats. Dan is sick. • Cook(George) Eat(Dan) Sick(Dan) • If George cooks and Dan eats, Dan will get sick. (Cook(George) ^ eat(Dan))  Sick(Dan) • Meaning derives from • The people and activities represented (predicates and arguments, or, nouns and verbs) • The way they are ordered and related: syntax of the representation, which may also reflect the syntax of the sentence CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

37. Syntax-Driven Semantics S NP VP eat(Dan) Nom V N Dan eats • So….can we link syntactic structures to a corresponding semantic representation to produce the ‘meaning’ of a sentence in the course of parsing it? CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

38. Specific vs. General-Purpose Rules • We don’t want to have to specify for every possible parse tree what semantic representation it maps to • We want to identify general mappings from parse trees to semantic representations • One approach: • Augment the lexicon and the grammar • Devise amapping between rules of the grammar and rules of semantic representation CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

39. Semantic Attachments Extend each grammar rule with instructions on how to map the components of the rule to a semantic representation S  NP VP {VP.sem(NP.sem)} • Each semantic function defined in terms of the semantic representation of choice • Problem: how to define these functions and how to specify their composition so we always get the meaning representation we want from our grammar? CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

40. A Simple Example McDonald’s serves burgers. • Associating constants with constituents • ProperNoun  McDonald’s {McDonald’s} • PlNoun  burgers {burgers} • Defining functions to produce these from input • NP  ProperNoun {ProperNoun.sem} • NP  PlNoun {PlNoun.sem} • Assumption: meaning representations of children are passed up to parents for non-branching constuents • Verbs are where the action is CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

41. V  serves {E(e,x,y) Isa(e,Serving) ^ Server(e,x) ^ Served(e,y)} where e = event, x = agent, y = patient • Will every verb have its own distinct representation? • McDonald’s hires students. • McDonald’s gave customers a bonus. • Predicate(Agent, Patient, Beneficiary) • Typically, divide verbs into classes based on what roles participate in the verb. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

42. Doing Compositional Semantics • To incorporate semantics into grammar we must • Figure out right representation for each constituent based on the parts of that constituent (e.g. Adj) • Figure out the right representation for a category of constituents based on other grammar rules, making use of that constituent (e.g. V.sem) • This gives us a set of function-like semantic attachments incorporated into our CFG • E.g. Nom  Adj Nom {x Nom.sem(x) ^ Isa(x,Adj.sem)} CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

43. What do we do with them? • Alter a parser such as an Early-style parser so when constituents (dot at the end of the rule) are completed, the attached semantic is function applied and meaning representation is created and stored with state • Or, let parser run to completion and then walk through resulting tree running semantic attachments from bottom-up CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

44. Option 1 (Integrated Semantic Analysis) S  NP VP {VP.sem(NP.sem)} • VP.sem has been stored in state representing VP • NP.sem stored with the state for NP • When rule completed, retrieve value of VP.sem and of NP.sem, and apply VP.sem to NP.sem • Store result in S.sem. • As fragments of input parsed, semantic fragments created • Can be used to block ambiguous representations • But: you also perform semantic analysis on orphaned constituents that play no role in final parse CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

45. Option 2: Post-hoc Semantic Analysis • Do semantics after syntactic parse • Don’t do any semantic work on constituents we will back out of – can be a significant efficiency gain • But can’t use semantics to aid the parse. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

46. Compositional Semantics Summary • Hypothesis: Principle of Compositionality • Semantics of NL sentences and phrases can be composed from the semantics of their subparts • Rules can be derived which map syntactic analysis to semantic representation (Rule-to-Rule Hypothesis) • Parsing and mapping can be done during syntactic analysis or as a separate phase. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

47. Non-Compositional Language • What do we do with language whose meaning isn’t derived from the meanings of its parts • Non-compositional modifiers: fake, former, local • Metaphor: • You’re the cream in my coffee. She’s the cream in George’s coffee. • The break-in was just the tip of the iceberg. This was only the tip of Shirley’s iceberg. • Idioms: • The old man finally kicked the bucket. The old man finally kicked the proverbial bucket. • Deferred reference: The ham sandwich wants his check. • Mix lexical items with special grammar rules? Take a totally different approach? CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

48. Feature and Information Extraction • We don’t always need a complete parse. • We may be after only some specific information • And we know what that information is • 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. • We don’t care at all about the information in red • Other semantic methods are more useful here. CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

49. Feature Extraction • Group individual terms into more complex entities (which in turn become tokens) • Examples • Dates, times, names, places • URLs, HREFs and IMG tags • Relationships like “X is president of Y” • Can involve quite high-level features: language of a sample of text • Not usually a goal in itself • In this case we are generating semantics for further use by an application CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari

50. Feature Extraction • Human-meaningful features: Parse token stream, applying pattern-matching rules • general, broadly applicable features (dates) • domain-specific features (chemical names) • Can involve very sophisticated domain knowledge. • Statistical features: • document length, vocabulary used, sentence length, document complexity, etc, etc • Often first step in document-based analysis such as classification CSC 9010: Special Topics, Natural Language Processing. Spring, 2005. Matuszek & Papalaskari