1. 10/3/2015CPSC503 Winter 20091 CPSC 503 Computational Linguistics Lecture 8 Giuseppe Carenini

2. 10/3/2015CPSC503 Winter 20092 Today 1/10 Finish POS tagging Start Syntax / Parsing (Chp 12!)

3. 10/3/2015CPSC503 Winter 20093 Evaluating Taggers Accuracy: percent correct (most current taggers 96-7%) *test on unseen data!* Human Celing: agreement rate of humans on classification (96-7%) Unigram baseline: assign each token to the class it occurred in most frequently in the training set (race -> NN). (91%) What is causing the errors? Build a confusion matrix…

4. 10/3/2015CPSC503 Winter 20094 Confusion matrix Precision ? Recall ?

5. 10/3/2015CPSC503 Winter 20095 Error Analysis (textbook) Look at a confusion matrix See what errors are causing problems –Noun (NN) vs ProperNoun (NNP) vs Adj (JJ) –Past tense (VBD) vs Past Participle (VBN)

6. 10/3/2015CPSC503 Winter 20096 Knowledge-Formalisms Map (next three lectures) Logical formalisms (First-Order Logics) Rule systems (and prob. versions) (e.g., (Prob.) Context-Free Grammars) State Machines (and prob. versions) (Finite State Automata,Finite State Transducers, Markov Models) Morphology Syntax Pragmatics Discourse and Dialogue Semantics AI planners

7. 10/3/2015CPSC503 Winter 20097 Today 1/10 Finish POS tagging English Syntax Context-Free Grammar for English –Rules –Trees –Recursion –Problems Start Parsing

8. 10/3/2015CPSC503 Winter 20098 Syntax Def. The study of how sentences are formed by grouping and ordering words Example: Ming and Sue prefer morning flights * Ming Sue flights morning and prefer Groups behave as single unit wrt Substitution, Movement, Coordination

9. 10/3/2015CPSC503 Winter 20099 Syntax: Useful tasks Why should you care? –Grammar checkers –Basis for semantic interpretation Question answering Information extraction Summarization –Machine translation –……

10. 10/3/2015CPSC503 Winter 200910 Key Constituents – with heads (English) Noun phrases Verb phrases Prepositional phrases Adjective phrases Sentences (Det) N (PP) (Qual) V (NP) (Deg) P (NP) (Deg) A (PP) (NP) (I)(VP) Some simple specifiers Category Typical functionExamples Determiner specifier of N the, a, this, no.. Qualifier specifier of V never, often.. Degree word specifier of A or P very, almost.. Complements? (Specifier) X (Complement)

11. 10/3/2015CPSC503 Winter 200911 Key Constituents: Examples Noun phrases Verb phrases Prepositional phrases Adjective phrases Sentences (Det) N (PP) the cat on the table (Qual) V (NP) never eat a cat (Deg) P (NP) almost inthe net (Deg) A (PP) very happy about it (NP) (I)(VP) a mouse --ate it

12. 10/3/2015CPSC503 Winter 200912 Context Free Grammar (Example) S -> NP VP NP -> Det NOMINAL NOMINAL -> Noun VP -> Verb Det -> a Noun -> flight Verb -> left Terminal Non-terminal Start-symbol

13. 10/3/2015CPSC503 Winter 200913 CFG more complex Example LexiconGrammar with example phrases

14. 10/3/2015CPSC503 Winter 200914 CFGs Define a Formal Language (un/grammatical sentences) Generative Formalism –Generate strings in the language –Reject strings not in the language –Impose structures (trees) on strings in the language

15. 10/3/2015CPSC503 Winter 200915 CFG: Formal Definitions 4-tuple (non-term., term., productions, start) (N, , P, S) P is a set of rules A  ; A  N,  (  N)* A derivation is the process of rewriting  1 into  m ( both strings in (  N)*) by applying a sequence of rules:  1  *  m L G = W|w  * and S  * w

16. 10/3/2015CPSC503 Winter 200916 Derivations as Trees flight Nominal Context Free?

17. 10/3/2015CPSC503 Winter 200917 CFG Parsing It is completely analogous to running a finite-state transducer with a tape –It’s just more powerful Chpt. 13 Parser I prefer a morning flight flight Nominal

18. 10/3/2015CPSC503 Winter 200918 Other Options Regular languages (FSA) A  x B or A  x –Too weak (e.g., cannot deal with recursion in a general way – no center-embedding) CFGs A   (also produce more understandable and “useful” structure) Context-sensitive  A   ;  ≠  –Can be computationally intractable Turing equiv.  ;  ≠  –Too powerful / Computationally intractable

19. 10/3/2015CPSC503 Winter 200919 Common Sentence-Types Declaratives: A plane left S -> NP VP Imperatives: Leave! S -> VP Yes-No Questions: Did the plane leave? S -> Aux NP VP WH Questions: Which flights serve breakfast? S -> WH NP VP When did the plane leave? S -> WH Aux NP VP

20. 10/3/2015CPSC503 Winter 200920 NP: more details NP -> Specifiers N Complements NP -> (Predet)(Det)(Card)(Ord)(Quant) (AP) Nom e.g., all the other cheap cars Nom -> Nom PP (PP) (PP) e.g., reservation on BA456 from NY to YVR Nom -> Nom GerundVP e.g., flight arriving on Monday Nom -> Nom RelClause Nom RelClause ->(who | that) VP e.g., flight that arrives in the evening

21. 10/3/2015CPSC503 Winter 200921 Conjunctive Constructions S -> S and S –John went to NY and Mary followed him NP -> NP and NP –John went to NY and Boston VP -> VP and VP –John went to NY and visited MOMA … In fact the right rule for English is X -> X and X

22. 10/3/2015CPSC503 Winter 200922 Problems with CFGs Agreement Subcategorization

23. 10/3/2015CPSC503 Winter 200923 Agreement In English, –Determiners and nouns have to agree in number –Subjects and verbs have to agree in person and number Many languages have agreement systems that are far more complex than this (e.g., gender).

24. 10/3/2015CPSC503 Winter 200924 Agreement This dog Those dogs This dog eats You have it Those dogs eat *This dogs *Those dog *This dog eat *You has it *Those dogs eats

25. 10/3/2015CPSC503 Winter 200925 Possible CFG Solution S -> NP VP NP -> Det Nom VP -> V NP … SgS -> SgNP SgVP PlS -> PlNp PlVP SgNP -> SgDet SgNom PlNP -> PlDet PlNom PlVP -> PlV NP SgVP3p ->SgV3p NP … Sg = singular Pl = plural OLD GrammarNEW Grammar

26. 10/3/2015CPSC503 Winter 200926 CFG Solution for Agreement It works and stays within the power of CFGs But it doesn’t scale all that well (explosion in the number of rules)

27. 10/3/2015CPSC503 Winter 200927 Subcategorization *John sneezed the book *I prefer United has a flight *Give with a flight Def. It expresses constraints that a predicate (verb here) places on the number and type of its arguments (see first table)

28. 10/3/2015CPSC503 Winter 200928 Subcategorization Sneeze: John sneezed Find: Please find [a flight to NY] NP Give: Give [me] NP [a cheaper fare] NP Help: Can you help [me] NP [with a flight] PP Prefer: I prefer [to leave earlier] TO-VP Told: I was told [United has a flight] S …

29. 10/3/2015CPSC503 Winter 200929 So? So the various rules for VPs overgenerate. –They allow strings containing verbs and arguments that don’t go together –For example: VP -> V NP therefore Sneezed the book VP -> V S therefore go she will go there

30. 10/3/2015CPSC503 Winter 200930 Possible CFG Solution VP -> V VP -> V NP VP -> V NP PP … VP -> IntransV VP -> TransV NP VP -> TransPP to NP PP to … TransPP to -> hand,give,.. This solution has the same problem as the one for agreement OLD Grammar NEW Grammar

31. 10/3/2015CPSC503 Winter 200931 CFG for NLP: summary CFGs cover most syntactic structure in English. But there are problems (overgeneration) –That can be dealt with adequately, although not elegantly, by staying within the CFG framework. There are simpler, more elegant, solutions that take us out of the CFG framework: LFG, XTAGS… Chpt 15 “Features and Unification”

32. 10/3/2015CPSC503 Winter 200932 Dependency Grammars Syntactic structure: binary relations between words Links: grammatical function or very general semantic relation Abstract away from word-order variations (simpler grammars) Useful features in many NLP applications (for classification, summarization and NLG)

33. 10/3/2015CPSC503 Winter 200933 Today 2/10 English Syntax Context-Free Grammar for English –Rules –Trees –Recursion –Problems Start Parsing (if time left)

34. 10/3/2015CPSC503 Winter 200934 Parsing with CFGs Assign valid trees: covers all and only the elements of the input and has an S at the top Parser I prefer a morning flight flight Nominal CFG Sequence of words Valid parse trees

35. 10/3/2015CPSC503 Winter 200935 Parsing as Search S -> NP VP S -> Aux NP VP NP -> Det Noun VP -> Verb Det -> a Noun -> flight Verb -> left, arrive Aux -> do, does Search space of possible parse trees CFG defines Parsing : find all trees that cover all and only the words in the input

36. 10/3/2015CPSC503 Winter 200936 Constraints on Search Parser I prefer a morning flight flight Nominal CFG (search space) Sequence of wordsValid parse trees Search Strategies: Top-down or goal-directed Bottom-up or data-directed

37. 10/3/2015CPSC503 Winter 200937 Top-Down Parsing Since we’re trying to find trees rooted with an S (Sentences) start with the rules that give us an S. Then work your way down from there to the words. flight Input:

38. 10/3/2015CPSC503 Winter 200938 Next step: Top Down Space When POS categories are reached, reject trees whose leaves fail to match all words in the input ……..

39. 10/3/2015CPSC503 Winter 200939 Bottom-Up Parsing Of course, we also want trees that cover the input words. So start with trees that link up with the words in the right way. Then work your way up from there. flight

40. 10/3/2015CPSC503 Winter 200940 Two more steps: Bottom-Up Space flight ……..

41. 10/3/2015CPSC503 Winter 200941 Top-Down vs. Bottom-Up Top-down –Only searches for trees that can be answers –But suggests trees that are not consistent with the words Bottom-up –Only forms trees consistent with the words –Suggest trees that make no sense globally

42. 10/3/2015CPSC503 Winter 200942 So Combine Them Top-down: control strategy to generate trees Bottom-up: to filter out inappropriate parses Top-down Control strategy: Depth vs. Breadth first Which node to try to expand next Which grammar rule to use to expand a node (left-most) (textual order)

43. 10/3/2015CPSC503 Winter 200943 Top-Down, Depth-First, Left-to- Right Search Sample sentence: “Does this flight include a meal?”

44. 10/3/2015CPSC503 Winter 200944 Example “Does this flight include a meal?”

45. 10/3/2015CPSC503 Winter 200945 flight Example “Does this flight include a meal?”

46. 10/3/2015CPSC503 Winter 200946 flight Example “Does this flight include a meal?”

47. 10/3/2015CPSC503 Winter 200947 Adding Bottom-up Filtering The following sequence was a waste of time because an NP cannot generate a parse tree starting with an AUX Aux

48. 10/3/2015CPSC503 Winter 200948 Bottom-Up Filtering CategoryLeft Corners SDet, Proper-Noun, Aux, Verb NPDet, Proper-Noun NominalNoun VPVerb Aux

49. 10/3/2015CPSC503 Winter 200949 Problems with TD-BU-filtering Ambiguity Repeated Parsing SOLUTION: Earley Algorithm (once again dynamic programming!)

50. 10/3/2015CPSC503 Winter 200950 For Next Time Read Chapter 13 (Parsing) Optional: Read Chapter 16 (Features and Unification) – skip algorithms and implementation

51. 10/3/2015CPSC503 Winter 200951 Grammars and Constituency Of course, there’s nothing easy or obvious about how we come up with right set of constituents and the rules that govern how they combine... That’s why there are so many different theories of grammar and competing analyses of the same data. The approach to grammar, and the analyses, adopted here are very generic (and don’t correspond to any modern linguistic theory of grammar).

52. 10/3/2015CPSC503 Winter 200952 Syntactic Notions so far... N-grams: prob. distr. for next word can be effectively approximated knowing previous n words POS categories are based on: –distributional properties (what other words can occur nearby) –morphological properties (affixes they take)