Carol Beer (Little Britain) - PowerPoint PPT Presentation

About This Presentation
Title:

Carol Beer (Little Britain)

Description:

Carol Beer (Little Britain) Computer says no Question Answering Lecture 1 (Today): Introduction; History of QA; Architecture of a QA system; Evaluation. – PowerPoint PPT presentation

Number of Views:250
Avg rating:3.0/5.0
Slides: 51
Provided by: Joha162
Category:

less

Transcript and Presenter's Notes

Title: Carol Beer (Little Britain)


1
Carol Beer (Little Britain)
2
Computer says no
3
Question Answering
  • Lecture 1 (Today)Introduction History of QA
    Architecture of a QA system Evaluation.
  • Lecture 2 (Friday)Question Classification NLP
    techniques for question analysis POS-tagging
    Parsing Semantic analysis WordNet.
  • Lecture 3 (Next Monday)Retrieving Answers
    Document pre-processing Tokenisation Stemming
    Lemmatisation Named Entity Recognition Anaphora
    Resolution Matching Use of knowledge resources
    Reranking Sanity checking.

4
What is Question Answering?
  • ?

5
Information Pinpointing
  • Information required Average number of car
    accidents per year in Sweden.
  • Two ways of getting this information
  • Ask Google or a similar search engine (good
    luck!)
  • Ask a QA system the questionWhats the rate of
    car accidents in Sweden?

6
QA vs IR
  • Traditional method for information access IR
    (Information Retrieval)
  • Think of IR as finding the right book in a
    library
  • Think of QA as a librarian giving you the book
    and opening it on the page with the information
    youre looking for

7
QA vs IE
  • Traditional method for information access IE
    (Information Extraction)
  • Think of IE as finding answers to a pre-defined
    question (i.e., a template)
  • Think of QA as asking any question you like

8
What is Question Answering?
  • Questions in natural language, not queries!
  • Answers, not documents!

9
Why do we need QA?
  • Information overload problem
  • Accessing information using traditional methods
    such as IR and IE are limited
  • QA increasingly important because
  • Size of available information grows
  • There is duplicate information
  • There is false information
  • More and more computer illiterates accessing
    electronically stored information

10
Information Avalanche
  • Available information is growing
  • 1999 250MB pp for each person on earth
  • 2002 800MB pp for each person on earth
  • People want specific information
  • source M.de Rijke
    2005

11
People ask Questions
source M.de Rijke 2005
12
Why is QA hard? (1/3)
  • Questions are expressed in natural language (such
    as English or Italian)
  • Unlike formal languages, natural languages allow
    a great deal of flexibility
  • Example
  • What is the population of Rome?
  • How many people live in Rome?
  • Whats the size of Rome?
  • How many inhabitants does Rome have?

13
Why is QA hard? (2/3)
  • Answers are expressed in natural language (such
    as English or Italian)
  • Unlike formal languages, natural languages allow
    a great deal of flexibility
  • Example
  • is estimated at 2.5 million residents
  • current population of Rome is 2817000
  • Rome housed over 1 million inhabitants

14
Why is QA hard? (3/3)
  • Answers could be spread across different
    documents
  • Examples
  • Which European countries produce wine?Document
    A contains information about Italy, and document
    B about France
  • What does Bill Clintons wife do for a
    living?Document A explains that Bill Clintons
    wife is Hillary Clinton, and Document B tells us
    that shes a politician

15
History of QA (de Rijke Webber 2003)
  • QA is by no means a new area!
  • Simmons (1965) reviews 15 implemented and working
    systems
  • Many ingredients of todays QA systems are rooted
    in these early approaches
  • Database oriented systems, domain independent, as
    opposed to todays systems that work on large
    sets of unstructured texts

16
Examples of early QA systems
  • BASEBALL (Green et al. 1963)Answers English
    questions about scores, locations and dates of
    baseball games
  • LUNAR (Woods 1977)Accesses chemical data on
    lunar material compiled during the Apollo
    missions
  • PHLIQA1 (Scha et al. 1980)Answers short
    questions against a database of computer
    installations in Europe

17
Recent work in QA
  • Since the 1990s research in QA has by and large
    focused on open-domain applications
  • Recently interest in restricted-domain QA has
    increased, in particular in commercial
    applications
  • Banking, entertainment, etc.

18
Architecture of a QA system
corpus
IR
query
Question Analysis
question
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
19
Question Analysis
  • InputNatural Language Question
  • OutputExpected Answer Type(Formal)
    Representation of Question
  • Techniques usedMachine learning, parsing

20
Document Analysis
  • InputDocuments or Passages
  • Output(Formal) Representation of Passages that
    might contain the answer
  • Techniques usedTokenisation, Named Entity
    Recognition, Parsing

21
Answer Retrieval
  • InputExpected Answer TypeQuestion (formal
    representation)Passages (formal representation)
  • OutputRanked list of answers
  • Techniques usedMatching, Re-ranking, Validation

22
Example Run
corpus
IR
query
Question Analysis
question
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
23
Example Run
How long is the river Thames?
corpus
IR
query
Question Analysis
question
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
24
Example Run
length river thames
corpus
IR
query
Question Analysis
question
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
25
Example Run
corpus
MEASURE
IR
query
Question Analysis
question
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
26
Example Run
corpus
IR
query
Question Analysis
question
Answer(x) length(y,x) river(y)
named(y,thames)
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
27
Example Run
A NYT199802-31 B APW199805-12 C NYT200011-07
corpus
IR
query
Question Analysis
question
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
28
Example Run
A 30(u) mile(u) length(v,u) river(y) B
60(z) centimeter(z) height(v,z) dog(z) C
230(u) kilometer(u) length(x,u) river(x)
corpus
IR
query
Question Analysis
question
documents/passages
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
29
Example Run
corpus
IR
query
Question Analysis
question
documents/passages
C 230 kilometer A 30 milesB 60 centimeter
Document Analysis
answer-type
question representation
passage representation
Answer Extraction
answers
30
Evaluating QA systems
  • International evaluation campaigns for QA systems
    (open domain QA)
  • TREC (Text Retrieval Conference)http//trec.nist.
    gov/
  • CLEF (Cross Language Evaluation
    Forum)http//clef-qa.itc.it/
  • NTCIR (NII Test Collection for IR
    Systems)http//www.slt.atr.jp/CLQA/

31
TREC-QA (organised by NIST)
  • Annual event, started in 1999
  • Difficulty of the QA task increased over the
    years
  • 1999 Answers in snippets, ranked list of
    answers
  • 2005 Exact answers, only one answer.
  • Three types of questions
  • Factoid questions
  • List questions
  • Definition questions

32
QA_at_CLEF
  • CLEF is the European edition of TREC
  • Monolingual (non-English) QA
  • Bulgarian (BG), German (DE), Spanish (ES),
    Finnish (FI), French (FR), Italian (IT), Dutch
    (NL), Portuguese (PT)
  • Cross-Lingual QA
  • Questions posed in source language, answer
    searched in documents of target language
  • All combinations possible

33
Open-Domain QA
  • QA at TREC is considered Open-Domain QA
  • Document collection is Acquint Corpus(over a
    million documents)
  • Questions can be about anything
  • Restricted-Domain QA
  • Documents described a specific domain
  • Detailed questions
  • Less redundancy of answers!

34
TREC-type questions
  • Factoid questions
  • Where is the Taj Mahal?
  • List questions
  • What actors have played Tevye in Fiddler on the
    Roof'?
  • Definition/biographical questions
  • What is a golden parachute?
  • Who is Vlad the Impaler?

35
What is a correct answer?
  • Example Factoid Question
  • When did Franz Kafka die?
  • Possible Answers
  • Kafka died in 1923.
  • Kafka died in 1924.
  • Kafka died on June 3, 1924 from complications
    related to Tuberculosis.
  • Ernest Watz was born June 3, 1924.
  • Kafka died on June 3, 1924.

36
What is a correct answer?
  • Example Factoid Question
  • When did Franz Kafka die?
  • Possible Answers
  • Kafka died in 1923.
  • Kafka died in 1924.
  • Kafka died on June 3, 1924 from complications
    related to Tuberculosis.
  • Ernest Watz was born June 3, 1924.
  • Kafka died on June 3, 1924.

Incorrect
37
What is a correct answer?
  • Example Factoid Question
  • When did Franz Kafka die?
  • Possible Answers
  • Kafka died in 1923.
  • Kafka died in 1924.
  • Kafka died on June 3, 1924 from complications
    related to Tuberculosis.
  • Ernest Watz was born June 3, 1924.
  • Kafka died on June 3, 1924.

Inexact (under-informative)
38
What is a correct answer?
  • Example Question
  • When did Franz Kafka die?
  • Possible Answers
  • Kafka died in 1923.
  • Kafka died in 1924.
  • Kafka died on June 3, 1924 from complications
    related to Tuberculosis.
  • Ernest Watz was born June 3, 1924.
  • Kafka died on June 3, 1924.

Inexact (over-informative)
39
What is a correct answer?
  • Example Question
  • When did Franz Kafka die?
  • Possible Answers
  • Kafka died in 1923.
  • Kafka died in 1924.
  • Kafka died on June 3, 1924 from complications
    related to Tuberculosis.
  • Ernest Watz was born June 3, 1924.
  • Kafka died on June 3, 1924.

Unsupported
40
What is a correct answer?
  • Example Question
  • When did Franz Kafka die?
  • Possible Answers
  • Kafka died in 1923.
  • Kafka died in 1924.
  • Kafka died on June 3, 1924 from complications
    related to Tuberculosis.
  • Ernest Watz was born June 3, 1924.
  • Kafka died on June 3, 1924.

Correct
41
Answer Accuracy
  • correct
    answers
  • Answer Accuracy ---------------------------

  • questions

42
Correct answers to list questions
Example List Question Which European countries
produce wine?
  • System A
  • France
  • Italy

System B Scotland France
Germany Italy Spain
Iceland Greece the Netherlands Japan
Turkey Estonia
43
Evaluation metrics for list questions
  • Precision (P)
    answers judged correct distinct
    P ------------------------------------------
    ----
    answers returned
  • Recall (R) answers
    judged correct distinct R
    ------------------------------------------------
    total
    answers
  • F-Score (F) 2PR
    F ------------
    PR

44
Correct answers to list questions
Example List Question Which European countries
produce wine?
  • System A
  • France
  • Italy

System B Scotland France
Germany Italy Spain
Iceland Greece the Netherlands Japan
Turkey Estonia
P 1.00 R 0.25 F 0.40
P 0.64 R 0.88 F 0.74
45
Other evaluation metrics
  • System A Ranked answers (Accuracy 0.2)

Q1 Q2 Q3 Q4 Q6 Q7 Q8 Q9 . Qn
A1 W W C W C W W W . W
A2 W W W W W W W W . W
A3 W W W W W W W W . W
A4 W W W W W W W W . W
A5 W C W W W C W W . W
System B Ranked answers (Accuracy 0.1)
Q1 Q2 Q3 Q4 Q6 Q7 Q8 Q9 . Qn
A1 W W W W C W W W . W
A2 C W C W W C C W . C
A3 W C W W W W W W . W
A4 W W W C W W W W . W
A5 W W W W W W W W . W
46
Mean Reciprocal Rank (MRR)
  • Score for an individual question
  • The reciprocal of the rank at which the first
    correct answer is returned
  • 0 if no correct response is returned
  • The score for a run
  • Mean over the set of questions in the test

47
MRR in action
  • System A MRR (.211.2)/10 0.24

Q1 Q2 Q3 Q4 Q6 Q7 Q8 Q9 . Qn
A1 W W C W C W W W . W
A2 W W W W W W W W . W
A3 W W W W W W W W . W
A4 W W W W W W W W . W
A5 W C W W W C W W . W
System B MRR (.5.33.5.251.5.5.5)/100.42
Q1 Q2 Q3 Q4 Q6 Q7 Q8 Q9 . Qn
A1 W W W W C W W W . W
A2 C W C W W C C W . C
A3 W C W W W W W W . W
A4 W W W C W W W W . W
A5 W W W W W W W W . W
48
Open-Domain Question Answering
  • TREC QA Track
  • Factoid questions
  • List questions
  • Definition questions
  • State-of-the-Art
  • Hard problem
  • Only few systems withgood results

49
Friday
  • QA Lecture 2
  • Question Classification
  • NLP techniques for question analysis
  • POS-tagging
  • Parsing
  • Semantic analysis
  • Use of lexical resources such as WordNet

50
Question Classification (preview)
  • How many islands does Italy have?
  • When did Inter win the Scudetto?
  • What are the colours of the Lithuanian flag?
  • Where is St. Andrews located?
  • Why does oil float in water?
  • How did Frank Zappa die?
  • Name the Baltic countries.
  • Which seabird was declared extinct in the 1840s?
  • Who is Noam Chomsky?
  • List names of Russian composers.
  • Edison is the inventor of what?
  • How far is the moon from the sun?
  • What is the distance from New York to Boston?
  • How many planets are there?
  • What is the exchange rate of the Euro to the
    Dollar?
  • What does SPQR stand for?
  • What is the nickname of Totti?
  • What does the Scottish word bonnie mean?
  • Who wrote the song Paranoid Android?
Write a Comment
User Comments (0)
About PowerShow.com