Question Generation with Minimal Recursion Semantics Xuchen Yao - - PowerPoint PPT Presentation

▶
question generation with minimal recursion semantics
SMART_READER_LITE
LIVE PREVIEW

Question Generation with Minimal Recursion Semantics Xuchen Yao - - PowerPoint PPT Presentation

Mar 18, 2023 197 likes •711 views

Question Generation with Minimal Recursion Semantics Xuchen Yao European Masters in Language and Communication Technologies Supervisors: Prof. Hans Uszkoreit and Dr. Yi Zhang, Saarland University Co-supervisor: Dr. Gosse Bouma, University of

slide-1
SLIDE 1

Question Generation with Minimal Recursion Semantics

Xuchen Yao

European Masters in Language and Communication Technologies Supervisors: Prof. Hans Uszkoreit and Dr. Yi Zhang, Saarland University Co-supervisor: Dr. Gosse Bouma, University of Groningen

28 July 2010, Master Colloquium

slide-2
SLIDE 2

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-3
SLIDE 3

Introduction Background System Architecture Evaluation Conclusion

Question Generation (QG)

The task of generating reasonable questions from a text.

Deep QG: why, why not, what-if, what-if-not, how Shallow QG:.who, what, when, where, which, how many/much, yes/no Jackson was born on August 29, 1958 in Gary, Indiana.

  • Who was born on August 29 , 1958 in Gary , Indiana?
  • Which artist was born on August 29 , 1958 in Gary , Indiana?
  • Where was Jackson born?
  • When was Jackson born?
  • Was Jackson born on August 29 , 1958 in Gary , Indiana?
slide-4
SLIDE 4

Introduction Background System Architecture Evaluation Conclusion

Question Generation (QG)

The task of generating reasonable questions from a text.

Deep QG: why, why not, what-if, what-if-not, how Shallow QG:.who, what, when, where, which, how many/much, yes/no Jackson was born on August 29, 1958 in Gary, Indiana.

  • Who was born on August 29 , 1958 in Gary , Indiana?
  • Which artist was born on August 29 , 1958 in Gary , Indiana?
  • Where was Jackson born?
  • When was Jackson born?
  • Was Jackson born on August 29 , 1958 in Gary , Indiana?
slide-5
SLIDE 5

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-6
SLIDE 6

Introduction Background System Architecture Evaluation Conclusion

Usage

  • Intelligent tutoring systems
  • QG can ask learners questions based on learning materials in
  • rder to check their accomplishment or help them focus on the

keystones in study.

  • QG can also help tutors to prepare questions intended for

learners or prepare for questions possibly from learners.

  • Closed-domain question answering (QA) systems
  • Some closed-domain QA systems use pre-defined (sometimes

hand-written) question-answer pairs to provide QA services.

  • By employing a QG approach such systems could expand to
  • ther domains with a small effort.
slide-7
SLIDE 7

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-8
SLIDE 8

Introduction Background System Architecture Evaluation Conclusion

Approaches

  • Template-based
  • What did <character> <verb>?
  • Syntax-based
  • John plays football. (S V O)
  • John plays what? (S V WHNP)
  • John does play what? (S Aux-V V WHNP)
  • Does John play what? (Aux-V S V WHNP)
  • What does John play? (WHNP Aux-V S V)
  • Semantics-based
  • play(John, football)
  • play(who, football)
  • play(John, what) || play(John, what sport)
slide-9
SLIDE 9

Introduction Background System Architecture Evaluation Conclusion

Approaches

  • Template-based
  • What did <character> <verb>?
  • Syntax-based
  • John plays football. (S V O)
  • John plays what? (S V WHNP)
  • John does play what? (S Aux-V V WHNP)
  • Does John play what? (Aux-V S V WHNP)
  • What does John play? (WHNP Aux-V S V)
  • Semantics-based
  • play(John, football)
  • play(who, football)
  • play(John, what) || play(John, what sport)
slide-10
SLIDE 10

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-11
SLIDE 11

Introduction Background System Architecture Evaluation Conclusion

DELPH-IN (MRS/ERG/PET/LKB)

Deep Linguistic Processing with HPSG: http://www.delph-in.net/ INDEX: e2 RELS: < [ PROPER_Q_REL<0:4> LBL: h3 ARG0: x6 RSTR: h5 BODY: h4 ] [ _like_v_1_rel<5:10> LBL: h8 ARG0: e2 [ e SF: PROP TENSE: PRES ] ARG1: x6 ARG2: x9 [ PROPER_Q_REL<11:17> LBL: h10 ARG0: x9 RSTR: h12 BODY: h11 ] > HCONS: < h5 qeq h7 h12 qeq h13 > [ NAMED_REL<0:4> LBL: h7 ARG0: x6 (PERS: 3 NUM: SG) CARG: "John" ] [ NAMED_REL<11:17> LBL: h13 ARG0: x9 (PERS: 3 NUM: SG) CARG: "Mary" ]

John likes Mary. like(John, Mary)

Parsing with PET Generation with LKB

John likes Mary.

Minimal Recursion Semantics

English Resource Grammar

slide-12
SLIDE 12

Introduction Background System Architecture Evaluation Conclusion

Dependency MRS

like(John, Mary)

_like_v_1 named("John") proper_q rstr/h arg1/neq named("Mary") proper_q rstr/h arg2/neq

Figure: DMRS for “John likes Mary.”

slide-13
SLIDE 13

Introduction Background System Architecture Evaluation Conclusion

Initial Idea

like(John,Mary)->like(who,Mary)

_like_v_1 named("John") proper_q rstr/h arg1/neq named("Mary") proper_q rstr/h arg2/neq _like_v_1 person which_q rstr/h arg1/neq named("Mary") proper_q rstr/h arg2/neq

Figure: “John likes Mary” → “Who likes Mary?”

slide-14
SLIDE 14

Introduction Background System Architecture Evaluation Conclusion

Details

(THEORY)MRS: Minimal Recursion Semantics

a meta-level language for describing semantic structures in some underlying object language.

(GRAMMAR)ERG: English Resource Grammar

a general-purpose broad-coverage grammar implementation under the HPSG framework.

(TOOL)LKB: Linguistic Knowledge Builder

a grammar development environment for grammars in typed feature structures and unification-based formalisms.

(TOOL)PET: a platform for experimentation with efficient HPSG processing techniques

a two-stage parsing model with HPSG rules and PCFG models, balancing between precise linguistic interpretation and robust probabilistic coverage.

slide-15
SLIDE 15

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-16
SLIDE 16

Introduction Background System Architecture Evaluation Conclusion

MrsQG

http://code.google.com/p/mrsqg/

MRS XML

Plain text Term extraction FSC construction Parsing with PET 2 3 1 Generation with LKB Output selection 5 6 7 MRS

Transformation

MRS Decomposition 8 Output to console/XML

FSC XML

Apposition Decomposer Coordination Decomposer Subclause Decomposer Subordinate Decomposer Why Decomposer

MRS XML

4

slide-17
SLIDE 17

Introduction Background System Architecture Evaluation Conclusion

Term Extraction

MRS XML

Plain text Term extraction FSC construction Parsing with PET 2 3 1 Generation with LKB Output selection 5 6 7 MRS

Transformation

MRS Decomposition 8 Output to console/XML

FSC XML

Apposition Decomposer Coordination Decomposer Subclause Decomposer Subordinate Decomposer Why Decomposer

MRS XML

4

  • Stanford Named Entity Recognizer
  • a regular expression NE tagger
  • an Ontology NE tagger

Jackson was born on August 29, 1958 in Gary, Indiana.

who which day where which location NEperson NElocation NEdate when

slide-18
SLIDE 18

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-19
SLIDE 19

Introduction Background System Architecture Evaluation Conclusion

MRS Transformation

MRS XML

Plain text Term extraction FSC construction Parsing with PET 2 3 1 Generation with LKB Output selection 5 6 7 MRS

Transformation

MRS Decomposition 8 Output to console/XML

FSC XML

Apposition Decomposer Coordination Decomposer Subclause Decomposer Subordinate Decomposer Why Decomposer

MRS XML

4

slide-20
SLIDE 20

Introduction Background System Architecture Evaluation Conclusion

WHO

_like_v_1 named("John") proper_q rstr/h arg1/neq named("Mary") proper_q rstr/h arg2/neq _like_v_1 person which_q rstr/h arg1/neq named("Mary") proper_q rstr/h arg2/neq

Figure: “John likes Mary” → “Who likes Mary?”

slide-21
SLIDE 21

Introduction Background System Architecture Evaluation Conclusion

WHERE

_sing_v_1 named("Mary") proper_q rstr/h arg1/neq _on_p named("Broadway") proper_q rstr/h arg2/neq arg1/eq _sing_v_1 named("Mary") proper_q rstr/h arg1/neq loc_nonsp place_n which_q rstr/h arg2/neq arg1/eq

Figure: “Mary sings on Broadway.” → “Where does Mary sing?”

slide-22
SLIDE 22

Introduction Background System Architecture Evaluation Conclusion

WHEN

_sing_v_1 named("Mary") proper_q rstr/h arg1/neq at_p_temp numbered_hour("10") def_implict_q rstr/h arg2/neq arg1/eq _sing_v_1 named("Mary") proper_q rstr/h arg1/neq loc_nonsp time which_q rstr/h arg2/neq arg1/eq

Figure: “Mary sings at 10.” → “When does Mary sing?”

slide-23
SLIDE 23

Introduction Background System Architecture Evaluation Conclusion

WHY

_fight_v_1 named("John") proper_q rstr/h arg1/neq for_p named("Mary") proper_q rstr/h arg2/neq arg1/eq _fight_v_1 named("John") proper_q rstr/h arg1/neq for_p reason_q which_q rstr/h arg2/neq arg1/eq

Figure: “John fights for Mary.” → “Why does John fight?”

slide-24
SLIDE 24

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-25
SLIDE 25

Introduction Background System Architecture Evaluation Conclusion

Why?

Question Transformation does not Work Well without Sentence Simplification

Input Sentence: ASC takes a character as input, and returns the integer giving the ASCII code of the input character. Desired question: (a) What does ASC take as input? (b) What does ASC return? Actual questions that could have been generated from mrs transformation: (c) What does ASC take as input and returns the integer giving the ASCII code of the input character? (d) ASC takes a character as input and returns what giving the ASCII code of the input character?

slide-26
SLIDE 26

Introduction Background System Architecture Evaluation Conclusion

Why?

Question Transformation does not Work Well without Sentence Simplification

Input Sentence: ASC takes a character as input, and returns the integer giving the ASCII code of the input character. Desired question: (a) What does ASC take as input? (b) What does ASC return? Actual questions that could have been generated from mrs transformation: (c) What does ASC take as input and returns the integer giving the ASCII code of the input character? (d) ASC takes a character as input and returns what giving the ASCII code of the input character?

slide-27
SLIDE 27

Introduction Background System Architecture Evaluation Conclusion

MRS Decomposition

Complex Sentences -> Simple Sentences

MRS XML

Plain text Term extraction FSC construction Parsing with PET 2 3 1 Generation with LKB Output selection 5 6 7 MRS

Transformation

MRS Decomposition 8 Output to console/XML

FSC XML

Apposition Decomposer Coordination Decomposer Subclause Decomposer Subordinate Decomposer Why Decomposer

MRS XML

4

slide-28
SLIDE 28

Introduction Background System Architecture Evaluation Conclusion

Coordination Decomposer

“John likes cats very much but hates dogs a lot.”

but c like v 1 cat n 1 udef q rstr/h arg2/neq very+much a 1 arg1/eq l-hndl/heq l-index/neq named(”John”) proper q rstr/h hate v 1 dog n 1 udef q rstr/h arg2/neq a+lot a 1 arg1/eq r-hndl/heq r-index/neq arg1/neq arg1/neq but c

slide-29
SLIDE 29

Introduction Background System Architecture Evaluation Conclusion

Coordination Decomposer

left: “John likes cats very much.“ right: “John hates dogs a lot.”

but c like v 1 cat n 1 udef q rstr/h arg2/neq named(”John”) proper q rstr/h arg1/neq very+much a 1 arg1/eq hate v 1 named(”John”) proper q rstr/h arg1/neq dog n 1 udef q rstr/h arg2/neq a+lot a 1 arg1/eq

slide-30
SLIDE 30

Introduction Background System Architecture Evaluation Conclusion

Subclause Decomposer

identifies the verb, extracts its arguments and reconstructs MRS

be v id named(”Bart”) proper q rstr/h arg1/neq cat n 1 the q rstr/h chase v 1 dog n 1 the q rstr/h arg2/neq arg1/eq arg2/neq be v id named(”Bart”) proper q rstr/h arg1/neq cat n 1 the q rstr/h arg2/neq be v id cat n 1 the q rstr/h chase v 1 dog n 1 the q rstr/h arg2/neq arg1/neq arg2/neq (a): Bart is the cat that chases the dog. (b): Bart is the cat. (c): The cat chases the dog. decompose(({ chase v 1},{}) decompose(({ be v id},{},keepEQ = 0)

slide-31
SLIDE 31

Introduction Background System Architecture Evaluation Conclusion

Connected Dependency MRS Graph

Connected DMRS Graph

A Connected DMRS Graph is a tuple G = (N, E, L, Spre, Spost) of: a set N, whose elements are called nodes; a set E of connected pairs of vertices, called edges; a function L that returns the associated label for edges in E; a set Spre of pre-slash labels and a set Spost of post-slash labels. Specifically, N is a set of all Elementary Predications (eps) defined in a grammar; Spre contains all pre-slash labels, namely {arg*, rstr, l-index, r- index, l-hndl, r-hndl, null}; Spost contains all post-slash labels, namely {eq, neq, h, heq, null}; L is defined as: L(x, y) = [pre/post, . . .]. For every node x, y ∈ N, L returns a list of pairs pre/post that pre ∈ Spre, post ∈ Spost. If pre = null, then the edge between (x, y) is directed: x is the governer, y is the dependant; otherwise the edge between x and y is not directed. If post = null, then y = null, x has no dependant by a pre relation.

slide-32
SLIDE 32

Introduction Background System Architecture Evaluation Conclusion

Generic Decomposing Algorithm

function decompose(rEPS, eEPS, relaxEQ = 1, keepEQ = 1) parameters: rEPS: a set of eps for which we want to find related eps. eEPS: a set of exception eps. relaxEQ: a boolean value of whether to relax the post-slash value from eq to neq for verbs and prepositions (optional, default:1). keepEQ: a boolean value of whether to keep verbs and prepositions with a post-slash eq value(optional, default:1). returns: a set of eps that are related to rEPS ;; assuming concurrent modification of a set is permitted in a for loop aEPS ← the set of all eps in the dmrs graph retEPS ← ∅ ;; initialize an empty set for tEP ∈ rEPS and tEP / ∈ eEPS do for ep ∈ aEPS and ep / ∈ eEPS and ep / ∈ rEPS do pre/post ← L(tEP, ep) ;; ep is the dependant of tEP if pre = null then ;; ep exists if relaxEQ and post = eq and (tEP is a verb ep or (tEP is a prepo- sition ep and pre = arg2)) then assign ep a new label and change its qeq relation accordingly end if retEPS.add(ep) aEPS.remove(ep) end if pre/post ← L(ep, tEP) ;; ep is the governor of tEP if pre = null then ;; ep exists if keepEQ = 0 and ep is a (verb ep or preposition ep) and post = eq and ep has no empty arg* then continue ;; continue the loop without going further below end if retEPS.add(ep) aEPS.remove(ep) end if end for end for if retEPS = ∅ then return rEPS ∪ decompose(retEPS, eEPS, relaxEQ = 0) ;; the union

  • f two

else return rEPS end if

slide-33
SLIDE 33

Introduction Background System Architecture Evaluation Conclusion

English Sentence Structure

and corresponding decomposers

English Sentence Structure Complex dependent clause + independent clause Subordinate Clause Causal | Non-causal Relative Clause Compound coordination

  • f sentences

Simple independent & simple clause Coordination

  • f phrases

Apposition Others Coordination Subclause Subordinate Why Apposition Decomposer Pool Decomposed Sentence

slide-34
SLIDE 34

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-35
SLIDE 35

Introduction Background System Architecture Evaluation Conclusion

The Problem

Will the wedding be held next Monday?

MRS XML

Plain text Term extraction FSC construction Parsing with PET 2 3 1 Generation with LKB Output selection 5 6 7 MRS

Transformation

MRS Decomposition 8 Output to console/XML

FSC XML

Apposition Decomposer Coordination Decomposer Subclause Decomposer Subordinate Decomposer Why Decomposer

MRS XML

4 Unranked Realizations from LKB for “Will the wedding be held next Monday?” Next Monday the wedding will be held? Next Monday will the wedding be held? Next Monday, the wedding will be held? Next Monday, will the wedding be held? The wedding will be held next Monday? Will the wedding be held next Monday?

slide-36
SLIDE 36

Introduction Background System Architecture Evaluation Conclusion

Question Ranking

Will the wedding be held next Monday?

MaxEnt Model for Declaratives 4.31 The wedding will be held next Monday? 1.63 Will the wedding be held next Monday? 1.35 Next Monday the wedding will be held? 1.14 Will the wedding be held next Monday? 0.77 Next Monday, the wedding will be held? 0.51 Next Monday will the wedding be held? 0.29 Next Monday, will the wedding be held? Language Model for Interrogatives 1.97 Next Monday will the wedding be held? 1.97 Will the wedding be held next Monday? 1.97 Will the wedding be held next Monday? 1.38 Next Monday, will the wedding be held? 1.01 The wedding will be held next Monday? 0.95 Next Monday the wedding will be held? 0.75 Next Monday, the wedding will be held? Combined Scores 1.78 Will the wedding be held next Monday? 1.64 The wedding will be held next Monday? 1.44 Will the wedding be held next Monday? 1.11 Next Monday the wedding will be held? 0.81 Next Monday will the wedding be held? 0.76 Next Monday, the wedding will be held? 0.48 Next Monday, will the wedding be held?

slide-37
SLIDE 37

Introduction Background System Architecture Evaluation Conclusion

Review of System Architecture

MRS XML

Plain text Term extraction FSC construction Parsing with PET 2 3 1 Generation with LKB Output selection 5 6 7 MRS

Transformation

MRS Decomposition 8 Output to console/XML

FSC XML

Apposition Decomposer Coordination Decomposer Subclause Decomposer Subordinate Decomposer Why Decomposer

MRS XML

4

slide-38
SLIDE 38

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-39
SLIDE 39

Introduction Background System Architecture Evaluation Conclusion

QGSTEC2010

The Question Generation Shared Task and Evaluation Challenge (QGSTEC) 2010

Task B: QG from Sentences.

Participants are given one complete sentence from which their system must generate questions.

  • 1. Relevance. Questions should be relevant to the input

sentence.

  • 2. Question type. Questions should be of the specified target

question type.

  • 3. Syntactic correctness and fluency. The syntactic

correctness is rated to ensure systems can generate sensible

  • utput.
  • 4. Ambiguity. The question should make sense when asked

more or less out of the blue.

  • 5. Variety. Pairs of questions in answer to a single input are

evaluated on how different they are from each other.

slide-40
SLIDE 40

Introduction Background System Architecture Evaluation Conclusion

QGSTEC2010

The Question Generation Shared Task and Evaluation Challenge (QGSTEC) 2010

Task B: QG from Sentences.

Participants are given one complete sentence from which their system must generate questions.

  • 1. Relevance. Questions should be relevant to the input

sentence.

  • 2. Question type. Questions should be of the specified target

question type.

  • 3. Syntactic correctness and fluency. The syntactic

correctness is rated to ensure systems can generate sensible

  • utput.
  • 4. Ambiguity. The question should make sense when asked

more or less out of the blue.

  • 5. Variety. Pairs of questions in answer to a single input are

evaluated on how different they are from each other.

slide-41
SLIDE 41

Introduction Background System Architecture Evaluation Conclusion

Test Set

  • 360 questions were required to be generated from 90 sentences
  • 8 question types: yes/no, which, what, when, how many,

where, why and who. Wikipedia OpenLearn YahooAnswers All sentence count 27 28 35 90 average length 22.11 20.43 15.97 19.20 question count 120 120 120 360

slide-42
SLIDE 42

Introduction Background System Architecture Evaluation Conclusion

Participants

  • Lethbridge, syntax-based, University of Lethbridge, Canada
  • MrsQG, semantics-based, Saarland University, Germany
  • JUQGG, rule-based, Jadavpur University, India.
  • WLV, syntax-based, University of Wolverhampton, UK
slide-43
SLIDE 43

Introduction Background System Architecture Evaluation Conclusion

Evaluation Grades

Relevance Question Type Correctness Ambiguity Variety

0.00 0.50 1.00 1.50 2.00 2.50 3.00 3.50 4.00

Results per criterion without penalty on missing questions

WLV MrsQG JUQGG Lethbridge Worst

slide-44
SLIDE 44

Introduction Background System Architecture Evaluation Conclusion

Generation Coverage

MrsQG WLV JUQGG Lethbridge 0.00% 10.00% 20.00% 30.00% 40.00% 50.00% 60.00% 70.00% 80.00% 90.00% 100.00%

Coverages on input and output (generating 360 questions from 90 sentences)

sentences questions

slide-45
SLIDE 45

Introduction Background System Architecture Evaluation Conclusion

Evaluation Grades

with penalty on missing questions

Relevance Question Type Correctness Ambiguity Variety

0.00 0.50 1.00 1.50 2.00 2.50 3.00 3.50 4.00

Results per criterion with penalty on missing questions

MrsQG WLV JUQGG Lethbridge Worst

slide-46
SLIDE 46

Introduction Background System Architecture Evaluation Conclusion

Evaluation Grades per Question Type

Relevance Question Type Correctness Ambiguity Variety

0.5 1 1.5 2 2.5 3 3.5 4

Performance of MrsQG per Question Type

yes/no(28) which(42) what(116) when(36) how many(44) where(28) why(30) who(30) worst(354)

slide-47
SLIDE 47

Introduction Background System Architecture Evaluation Conclusion

Outline

Introduction Definition Usage Template/Syntax/Semantics-based Approaches Background MRS/ERG/PET/LKB System Architecture Overview MRS Transformation for Simple Sentences MRS Decomposition for Complex Sentences Question Reranking Evaluation QGSTEC 2010

slide-48
SLIDE 48

Introduction Background System Architecture Evaluation Conclusion

Back to our one-line abstract

John plays football –(1)–> play(John, football) –(2)–> play(who, which sports) –(3)–> Who plays which sports?

Natural Language Text Natural Language Questions Symbol Representation for Text Symbol Representation for Questions NLU NLG Question Generation Simplification Ranking Transformation

slide-49
SLIDE 49

Introduction Background System Architecture Evaluation Conclusion

Conclusion

  • semantics-based (easy in theory, difficult in practice)
  • multi-linguality
  • cross-domain
  • deep grammar (worry less, wait more)
  • generation <-> grammaticality
  • heavy machinery
slide-50
SLIDE 50

Introduction Background System Architecture Evaluation Conclusion

Demo?

and never forget Fourier Transform: Xk =

N−1

  • n=0

xne−i2πk n

N