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
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
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?
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?
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
Introduction Background System Architecture Evaluation Conclusion Usage • Intelligent tutoring systems • QG can ask learners questions based on learning materials in order 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 other domains with a small effort.
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
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)
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)
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
Introduction Background System Architecture Evaluation Conclusion DELPH-IN (MRS/ERG/PET/LKB) Deep Linguistic Processing with HPSG: http://www.delph-in.net/ Minimal Recursion Semantics INDEX: e2 John likes Mary. RELS: < like(John, Mary ) [ PROPER_Q_REL<0:4> [ NAMED_REL<0:4> LBL: h3 LBL: h7 ARG0: x6 ARG0: x6 RSTR: h5 (PERS: 3 NUM: SG) Parsing BODY: h4 ] CARG: "John" ] with PET [ _like_v_1_rel<5:10> LBL: h8 ARG0: e2 [ e SF: PROP TENSE: PRES ] ARG1: x6 Generation ARG2: x9 with LKB [ NAMED_REL<11:17> [ PROPER_Q_REL<11:17> LBL: h13 LBL: h10 ARG0: x9 ARG0: x9 RSTR: h12 (PERS: 3 NUM: SG) CARG: "Mary" ] BODY: h11 ] > John likes Mary. English Resource HCONS: < h5 qeq h7 h12 qeq h13 > Grammar
Introduction Background System Architecture Evaluation Conclusion Dependency MRS like(John, Mary) _like_v_1 arg1/neq arg2/neq named("John") named("Mary") rstr/h rstr/h proper_q proper_q Figure: DMRS for “ John likes Mary. ”
Introduction Background System Architecture Evaluation Conclusion Initial Idea like(John,Mary)->like(who,Mary) _like_v_1 _like_v_1 arg2/neq arg1/neq arg1/neq arg2/neq person named("John") named("Mary") named("Mary") rstr/h rstr/h rstr/h rstr/h proper_q proper_q proper_q which_q Figure: “ John likes Mary ” → “ Who likes Mary? ”
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.
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
Introduction Background System Architecture Evaluation Conclusion MrsQG http://code.google.com/p/mrsqg/ 5 4 MRS Plain text MRS Decomposition Transformation MRS XML Apposition Decomposer 1 6 Term Generation extraction with LKB Coordination Decomposer Subclause Decomposer 2 7 FSC Output construction selection Subordinate Decomposer FSC XML 8 Output to 3 Parsing Why Decomposer MRS console/XML with PET XML
Introduction Background System Architecture Evaluation Conclusion Term Extraction 5 4 MRS ● Stanford Named Entity Recognizer Plain text MRS Decomposition Transformation ● a regular expression NE tagger ● an Ontology NE tagger MRS 1 6 XML Apposition Decomposer Term Generation extraction Coordination Decomposer with LKB where 2 7 Subclause Decomposer FSC Output which location who when which day construction selection Subordinate Decomposer FSC 3 XML 8 Jackson was born on August 29, 1958 in Gary, Indiana. Output to Why Decomposer Parsing MRS console/XML with PET XML NEperson NEdate NElocation
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
Introduction Background System Architecture Evaluation Conclusion MRS Transformation 5 4 MRS Plain text MRS Decomposition Transformation MRS 1 6 XML Apposition Decomposer Term Generation extraction with LKB Coordination Decomposer 2 7 Subclause Decomposer FSC Output construction selection Subordinate Decomposer FSC 3 8 XML Output to Parsing Why Decomposer MRS console/XML with PET XML
Introduction Background System Architecture Evaluation Conclusion WHO _like_v_1 _like_v_1 arg2/neq arg1/neq arg1/neq arg2/neq person named("John") named("Mary") named("Mary") rstr/h rstr/h rstr/h rstr/h proper_q proper_q proper_q which_q Figure: “ John likes Mary ” → “ Who likes Mary? ”
Introduction Background System Architecture Evaluation Conclusion WHERE _sing_v_1 _sing_v_1 arg1/eq arg1/neq arg1/neq arg1/eq _on_p named("Mary") named("Mary") loc_nonsp arg2/neq arg2/neq rstr/h rstr/h proper_q proper_q named("Broadway") place_n rstr/h rstr/h proper_q which_q Figure: “Mary sings on Broadway.” → “Where does Mary sing?”
Recommend
More recommend