1. © Johan Bos November 2005 Pub Quiz

2. © Johan Bos November 2005 Question Answering Lecture 1 (Last week): Introduction; History of QA; Architecture of a QA system; Evaluation. Lecture 2 (Today): Question Classification; NLP techniques for question analysis; Tokenisation; Lemmatisation; POS-tagging; Parsing; WordNet. Lecture 3 (Next lecture): Retrieving Answers; Document pre-processing; Named Entity Recognition; Anaphora Resolution; Matching; Reranking; Sanity checking.

3. © Johan Bos November 2005 Architecture of a QA system IR Question Analysis query Document Analysis Answer Extraction question answer-type question representation documents/passages passage representation corpus answers

4. © Johan Bos November 2005 Architecture of a QA system IR Question Analysis query Document Analysis Answer Extraction question answer-type question representation documents/passages passage representation corpus answers

5. © Johan Bos November 2005 Syntactically Distinguishing Questions Wh-questions: –Where was Franz Kafka born? –How many countries are member of OPEC? –Who is Thom Yorke? –Why did David Koresh ask the FBI for a word processor? –How did Frank Zappa die? –Which boxer beat Muhammed Ali?

6. © Johan Bos November 2005 Syntactically Distinguishing Questions Yes-no questions: –Does light have weight? –Scotland is part of England – true or false? Choice-questions: –Did Italy or Germany win the world cup in 1982? –Who is Harry Potter’s best friend – Ron, Hermione or Sirius?

7. © Johan Bos November 2005 Syntactically Distinguishing Questions Imperative: –Name four European countries that produce wine. –Give the date of birth of Franz Kafka. Declarative: –I would like to know when Jim Morrison was born.

8. © Johan Bos November 2005 Semantically Distinguishing Questions Divide questions according to their expected answer type Simple Answer-Type Typology: PERSON NUMERAL DATE MEASURE LOCATION ORGANISATION ENTITY

9. © Johan Bos November 2005 Expected Answer Types DATE: –When was JFK killed? –In what year did Rome become the capital of Italy?

10. © Johan Bos November 2005 Expected Answer Types DATE: –When was JFK killed? –In what year did Rome become the capital of Italy? PERSON: –Who won the Nobel prize for Peace? –Which rock singer wrote Lithium?

11. © Johan Bos November 2005 Expected Answer Types DATE: –When was JFK killed? –In what year did Rome become the capital of Italy? PERSON: –Who won the Nobel prize for Peace? –Which rock singer wrote Lithium? NUMERAL: –How many inhabitants does Rome have? –What’s the population of Scotland?

12. © Johan Bos November 2005 Focus and Topic Information expressed in a question can be structured into two parts: –the focus: information that is asked for –the topic: information about focus Example: How many inhabitants does Rome have? FOCUS TOPIC

13. © Johan Bos November 2005 We need to know how to process natural language!

14. © Johan Bos November 2005 Architecture of a QA system IR Question Analysis query Document Analysis Answer Extraction question answer-type question representation documents/passages passage representation corpus answers

15. © Johan Bos November 2005 Generating Query Terms Example 1: –Question: Who discovered prions? –Text A: Dr. Stanley Prusiner received the Nobel prize for the discovery of prions. –Text B: Prions are a kind of proteins that… Query terms?

16. © Johan Bos November 2005 Generating Query Terms Example 2: –Question: When did Franz Kafka die? –Text A: Kafka died in 1924. –Text B: Dr. Franz died in 1971. Query terms?

17. © Johan Bos November 2005 Generating Query Terms Example 3: –Question: How did actor James Dean die? –Text: James Dean was killed in a car accident. Query terms?

18. © Johan Bos November 2005 We need to know how to process natural language!

19. © Johan Bos November 2005 Architecture of a QA system IR Question Analysis query Document Analysis Answer Extraction question answer-type question representation documents/passages passage representation corpus answers

20. © Johan Bos November 2005 Difference in structure Example: –Question: When did Franz Kafka die? –Text A: The mother of Franz Kafka died in 1918.

21. © Johan Bos November 2005 Difference in structure Example: –Question: When did Franz Kafka die? –Text A: The mother of Franz Kafka died in 1918. –Text B: Kafka died in 1924.

22. © Johan Bos November 2005 Difference in structure Example: –Question: When did Franz Kafka die? –Text A: The mother of Franz Kafka died in 1918. –Text B: Kafka died in 1924. –Text C: Both Kafka and Lenin died in 1924.

23. © Johan Bos November 2005 Difference in structure Example: –Question: When did Franz Kafka die? –Text A: The mother of Franz Kafka died in 1918. –Text B: Kafka died in 1924. –Text C: Both Kafka and Lenin died in 1924. –Text D: Max Brod, a friend of Kafka, died in 1930.

24. © Johan Bos November 2005 We need to know how to process natural language!

25. © Johan Bos November 2005 We need ways to automate the process of manipulating natural language –Punctuation –The way words are composed –The relationship between wordforms –The relationship between words –The structure of phrases This is where NLP (Natural Language Processing) comes in! Natural Language is messy!

26. © Johan Bos November 2005 NLP Techniques Tokenisation Lemmatisation Part of Speech Tagging Syntactic analysis (parsing) WordNet

27. © Johan Bos November 2005 NLP Techniques Tokenisation Lemmatisation Part of Speech Tagging Syntactic analysis (parsing) WordNet

28. © Johan Bos November 2005 Tokenisation Tokenisation is the task that splits words from punctuation –Semicolons, colons ; : –exclamation marks, question marks ! ? –commas and full stops., –quotes “ ‘ ` Tokens are normally split by spaces

29. © Johan Bos November 2005 Tokenisation: Example 1 Input (9 tokens): When was the Buckingham Palace built in London, England?

30. © Johan Bos November 2005 Tokenisation: Example 1 Input (9 tokens): When was the Buckingham Palace built in London, England? Output (11 tokens): When was the Buckingham Palace built in London, England ?

31. © Johan Bos November 2005 Tokenisation: Example 2 Input (7 tokens): What year did "Snow White" come out?

32. © Johan Bos November 2005 Tokenisation: Example 2 Input (7 tokens): What year did "Snow White" come out? Output (10 tokens): What year did “ Snow White " come out ?

33. © Johan Bos November 2005 Tokenisation: combined words Combined words are split –I’d  I ’d –country’s  country ’s –won’t  will n’t –“don’t!”  “ do n’t ! “ Some Italian examples – gliel’ha detto  gli lo ha detto – posso prenderlo  posso prendere lo

34. © Johan Bos November 2005 Difficulties with tokenisation Abbreviations, acronyms –When was the U.S. invasion of Haiti? In particular if the abbreviation or acronym is the last word of a sentence –Look at next word: if in uppercase, then assume it is end of sentence –But think of cases such as Mr. Jones

35. © Johan Bos November 2005 Why is tokenisation important? To look up a word in an electronic dictionary (such as WordNet) For all subsequent stages of processing –Lemmatisation –Parsing

36. © Johan Bos November 2005 NLP Techniques Tokenisation Lemmatisation Part of Speech Tagging Syntactic analysis (parsing) WordNet

37. © Johan Bos November 2005 Lemmatisation Lemmatising means – grouping morphological variants of words under a single headword For example, you could take the words am, was, are, is, were, and been together under the word be

38. © Johan Bos November 2005 Lemmatisation Lemmatising means – grouping morphological variants of words under a single headword For example, you could take the words am, was, are, is, were, and been together under the word be

39. © Johan Bos November 2005 Lemmatisation Using linguistic terminology, the variants taken together form the lemma of a lexeme Lexeme: a “lexical unit”, an abstraction over specific constructions Other examples: dying, die, died, dies  die car, cars  car man, men  man

40. © Johan Bos November 2005 NLP Techniques Tokenisation Lemmatisation Part of Speech Tagging Syntactic analysis (parsing) WordNet

41. © Johan Bos November 2005 Traditional parts of speech Verb Noun Pronoun Adjective Adverb Preposition Conjunction Interjection

42. © Johan Bos November 2005 Parts of speech in NLP CLAWS1 (132 tags) Examples: NN singular common noun (boy, pencil... ) NN$ genitive singular common noun (boy's, parliament's... ) NNP singular common noun with word initial capital (Austrian, American, Sioux, Eskimo... ) NNP$ genitive singular common noun with word initial capital (Sioux', Eskimo's, Austrian's, American's,...) NNPS plural common noun with word initial capital (Americans,... ) NNPS$ genitive plural common noun with word initial capital (Americans‘, …) NNS plural common noun (pencils, skeletons, days, weeks... ) NNS$ genitive plural common noun (boys', weeks'... ) NNU abbreviated unit of measurement unmarked for number (in, cc, kg …) Penn Treebank (45 tags) Examples: JJ adjective (green, …) JJR adjective, comparative (greener,…) JJS adjective, superlative (greenest, …) MD modal (could, will, …) NN noun, singular or mass (table, …) NNS noun plural (tables, …) NNP proper noun, singular (John, …) NNPS proper noun, plural (Vikings, …) PDT predeterminer (both the boys) POS possessive ending (friend's) PRP personal pronoun (I, he, it, …) PRP$ possessive pronoun (my, his, …) RB adverb (however, usually, naturally, here, good, …) RBR adverb, comparative (better, …)

43. © Johan Bos November 2005 POS tagged example What year did “ Snow White " come out ?

44. © Johan Bos November 2005 POS tagged example What WP year NN did VBD “ Snow NNP White NNP " “ come VB out IN ?.

45. © Johan Bos November 2005 Why is POS-tagging important? To disambiguate words For instance, to distinguish “book” used as a noun from “book” used as a verb –I like that book –Did you book a room? Prerequisite for further processing stages, such as parsing

46. © Johan Bos November 2005 NLP Techniques Tokenisation Lemmatisation Part of Speech Tagging Syntactic analysis (parsing) WordNet

47. © Johan Bos November 2005 What is Parsing Parsing is the process of assigning a syntactic structure to a sequence of words The syntactic structure is defined using a grammar A grammar contains of a set of symbols (terminal and non-terminal symbols) and production rules (grammar rules) The lexicon is built over the terminal symbols (i.e., the words)

48. © Johan Bos November 2005 Syntactic Categories The non-terminal symbols correspond to syntactic categories –Det (determiner) –N (noun) –IV (intransitive verb) –TV (transitive verb) –PN (proper name) –Prep (preposition) –NP (noun phrase) the car –PP (prepositional phrase) at the table –VP (verb phrase) saw a car –S (sentence) Mia likes Vincent

49. © Johan Bos November 2005 Example Grammar Lexicon Det: which, a, the,… N: rock, singer, … IV: die, walk, … TV: kill, write,… PN: John, Lithium, … Prep: on, from, to, … Grammar Rules S  NP VP NP  Det N NP  PN N  N N N  N PP VP  TV NP VP  IV PP  Prep NP VP  VP PP

50. © Johan Bos November 2005 The Parser A parser automates the process of parsing The input of the parser is a string of words (possibly annotated with POS- tags) The output of a parser is a parse tree, connecting all the words The way a parse tree is constructed is also called a derivation

51. © Johan Bos November 2005 Derivation Example Which rock singer wrote Lithium

52. © Johan Bos November 2005 Lexical stage Det N N TV PN Which rock singer wrote Lithium

53. © Johan Bos November 2005 Use rule: NP  Det N NP Det N N TV PN Which rock singer wrote Lithium

54. © Johan Bos November 2005 Use rule: NP  PN NP NP Det N N TV PN Which rock singer wrote Lithium

55. © Johan Bos November 2005 Use rule: VP  TV NP VP NP NP Det N N TV PN Which rock singer wrote Lithium

56. © Johan Bos November 2005 Backtracking VP NP NP Det N N TV PN Which rock singer wrote Lithium

57. © Johan Bos November 2005 Use rule: N  N N VP N NP Det N N TV PN Which rock singer wrote Lithium

58. © Johan Bos November 2005 Use rule: NP  Det N NP VP N NP Det N N TV PN Which rock singer wrote Lithium

59. © Johan Bos November 2005 Use rule S  NP VP S NP VP N NP Det N N TV PN Which rock singer wrote Lithium

60. © Johan Bos November 2005 Syntactic “head” S NP VP N NP Det N N TV PN Which rock singer wrote Lithium

61. © Johan Bos November 2005 Parse Tree (another example) S NP N PP VP NP VP PP Det N Prep PN PN IV Prep NP The mother of Franz Kafka died in 1918

62. © Johan Bos November 2005 Syntactic head S NP N PP VP NP VP PP Det N Prep PN PN IV Prep NP The mother of Franz Kafka died in 1918

63. © Johan Bos November 2005 Using a parser Normally expects tokenised and POS-tagged input Example of wide-coverage parsers: –Charniak parser –Collins parser –RASP (Carroll & Briscoe) –CCG parser (Clark & Curran)

64. © Johan Bos November 2005 NLP Techniques Tokenisation Lemmatisation Part of Speech Tagging Syntactic analysis (parsing) WordNet

65. © Johan Bos November 2005 WordNet Electronic dictionary Not only words and definitions, but also relations between words Four parts of speech –Nouns –Verbs –Adjectives –Adverbs

66. © Johan Bos November 2005 WordNet SynSets Words are organised in SynSets A SynSet is a group of words with the same meaning --- in other words, a set of synonyms Example: { Rome, Roma, Eternal City, Italian Capital, capital of Italy}

67. © Johan Bos November 2005 Senses A word can have several different meanings Example: plant –A building for industrial labour –A living organism lacking the power of locomotion The different meanings of a word are called senses Therefore, one word can occur in more than one SynSet in WordNet

68. © Johan Bos November 2005 SynSet Example -{mug, mugful} = the quantity that can be held in a mug -{chump, fool, gull, mark, patsy, fall guy, sucker, soft touch, chump, mug} = a person who is gullible and easy to take advantage of -{countenance, physiognomy, phiz, visage, kisser, smiler, mug} = the human face

69. © Johan Bos November 2005 Hypernyms Hyperonomy is a WordNet relation defined among two SynSets –If A is a hypernym of B, then A is more generic then B The inverse of hyperonomy is hyponomy –If A is a hyponym of B, then A is more specific then B Use these relations transitively Examples: –“cow” and “horse” are hyponyms of “animal” –“publication” is a hypernym of “book”

70. © Johan Bos November 2005 Examples using WordNet Which rock singer … –singer is a hyponym of person, therefore expected answer type is PERSON What is the population of … –population is a hyponym of number, hence answer type NUMERAL

71. © Johan Bos November 2005 How to use NLP tools? There is a large set of tools available on the web, most of it free for research Examples of integrated text processing environment –GATE (University of Sheffield) –TTT (University of Edinburgh) –LingPipe –For a general ovewrview of NLP tools, see http://registry.dfki.de/

72. © Johan Bos November 2005 Question Answering Lecture 1 (Last week): Introduction; History of QA; Architecture of a QA system; Evaluation. Lecture 2 (Today): Question Classification; NLP techniques for question analysis; Tokenisation; Lemmatisation; POS-tagging; Parsing; WordNet. Lecture 3 (Next lecture): Retrieving Answers; Document pre-processing; Named Entity Recognition; Anaphora Resolution; Matching; Reranking; Sanity checking.