SlideShare a Scribd company logo
Yanghoon Kim, Hwanhee Lee, Joongbo Shin and Kyomin Jung
Improving Neural Question Generation
using Answer Separation
김양훈
Background
Neural question generation (NQG)
- Generating a question from a given text passage with deep neural networks.
Importance of NQG
- Generating questions for educational materials.
- Generating questions for improving QA systems.
NQG with target Answer
- Generating a question from a given text passage and a given target
answer(question target) with deep neural networks.
2
Original passage: John Francis O’hara was elected president of Notre Dame in 1934.
Generated question 1: Who was elected president of Notre Dame in 1934?
Generated question 2: When was John Francis O’hara elected president of Notre Dame?
Problem
Previous NQG systems suffer from a critical problem
- Some models don’t take the target answer into account.
- RNNs often follow a shallow generation process.
- Some models can’t well grasp the target answer(question target) .
- A sophisticated proportion of generated questions include word in the target
answer.
3
Original passage: John Francis O’Hara was elected president of Notre Dame in 1934.
Given target answer: John Francis O’hara
Correctly Generated question: Who was elected president of Notre Dame in 1934?
Incorrectly generated question: Who was elected John Francis?
Contribution
We propose answer-separated seq2seq
- Treats the target answer(question target) and the passage separately.
- Prevent the generated question from including words in the target answer.
- Better capture the information from both the target answer and the passage
- We propose keyword-net
- Model is consistently aware of the target answer.
- Extract the key information in the target answer.
- We use retrieval style word generator
- Take the word meaning into account when generating words.
4
Task Definition
5
Model
Base model
- We use RNN encoder-decoder with attention
Answer-separated seq2seq consist of
- Answer-separated passage encoder
- Target answer encoder
- Answer-separated decoder
- keyword-net
- Retrieval style word generator
6
Model
Answer-separated passage encoder
- A simple preprocessing of the input passage
- Original passage: Steve Jobs is the founder of Apple.
- Masked passage: Steve Jobs is the <a> .
- A one-layer bi-LSTM
Answer encoder
- A one-layer bi-LSTM
7
Model
Answer-separated decoder
- A one-layer LSTM
- keyword-net
- Let the model consistently be aware of the target answer.
- Extract key information.
- Passage: Steve Jobs is the founder of Apple
- Target answer: founder of Apple
8
Model
Answer-separated decoder
- Retrieval style word generator by (Ma et al. 2018)*
- seq2seq has tendency to memorize the sequence pattern rather than
reflecting word meanings
- The word generator produces words by querying the distributed word
representations.
*Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation 9
Experiment
Data
- Processed version of SQuAD 1.1
- Data split 1: 70,484/10,570/11,877 (train/dev/test)
- Data split 2: 86,635/8,965/8,964
Evaluation
Our model(Ass2s) outperform the previous state-of-the-art model
10
Experiment
Impact of answer separation
- Ability to capture target answer
- We checked if the target answer is included in the generated question
- AP : Answer position Feature (BIO scheme)
- (Song et al. 2018) used the copy mechanism.
11
Our model has better ability to generate the right question given the target answer
Experiment
Impact of answer separation
- Interrogative word prediction
- “What” takes up more than half of the whole training set
- “Which” : “Which year” can be represented as “When”
- “why”, “yes/no” : only takes up 1.5% and 1.2% of the training set.
12
Our model has better ability to predict the question type for the given target answer
Experiment
Impact of answer separation
- Attention from <answer>
- (a) is the attention matrix from our model
- (b) is the attention matrix from seq2seq + AP
- <a> token gives the highest attention weights to the interrogative word “who” in (a)
13
Experiment
Question generation for machine comprehension
- Use named entities as target answers, generate synthetic data for machine
comprehension system(QA net by Google).
- ALL : Evaluation result of SQuAD dev set(10k)
- NER : Evaluation result of partial SQuAD dev set(4k)
- answers of single named entity
14
Conclusion
We propose Answer-separated seq2seq for NQG
- Separate utilization of target answer and the passage(without target answer)
- By masking the target answer inside the passage
- By using keyword-net to extract key feature from target answer
- By using retrieval style word generator to capture word meaning information
- Our model can
- Reduce the probability that the target answer is included by the generated question
- Generate fluent and right question for the given passage and the target answer
- Better inference the type of question
Thank you for listening!
Code, paper: https://yanghoonkim.github.io
Questions: ad26kr@snu.ac.kr

More Related Content

Similar to Improving Neural Question Generation using Answer Separation.

Improving neural question generation using answer separation
Improving neural question generation using answer separationImproving neural question generation using answer separation
Improving neural question generation using answer separation
NAVER Engineering
 
Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...
Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...
Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...
Universitat Politècnica de Catalunya
 
ACL 2018 Recap
ACL 2018 RecapACL 2018 Recap
ACL 2018 Recap
NAVER Engineering
 
Natural Language Generation / Stanford cs224n 2019w lecture 15 Review
Natural Language Generation / Stanford cs224n 2019w lecture 15 ReviewNatural Language Generation / Stanford cs224n 2019w lecture 15 Review
Natural Language Generation / Stanford cs224n 2019w lecture 15 Review
changedaeoh
 
Deep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate HelpdeskDeep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Saurabh Saxena
 
Wecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochureWecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochure
BIPIN KAUSHIK
 
Wecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochureWecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochure
WeCP | We Create Problems
 
WISS QA Do it yourself Question answering over Linked Data
WISS QA Do it yourself Question answering over Linked DataWISS QA Do it yourself Question answering over Linked Data
WISS QA Do it yourself Question answering over Linked Data
Andre Freitas
 
American sign language recognizer
American sign language recognizerAmerican sign language recognizer
American sign language recognizer
Garrett Broughton, Architect/Engineer
 
Seminar2017
Seminar2017Seminar2017
Seminar2017
Abdullah Khorshed
 
Python week 2 2019 2020 for g10 by eng.osama ghandour
Python week 2 2019 2020 for g10 by eng.osama ghandourPython week 2 2019 2020 for g10 by eng.osama ghandour
Python week 2 2019 2020 for g10 by eng.osama ghandour
Osama Ghandour Geris
 
Building a Meta-search Engine
Building a Meta-search EngineBuilding a Meta-search Engine
Building a Meta-search Engine
Ayan Chandra
 
The Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and BeyondThe Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and Beyond
NUS-ISS
 
Python week 1 2020-2021
Python week 1 2020-2021Python week 1 2020-2021
Python week 1 2020-2021
Osama Ghandour Geris
 
rlhf.pdf
rlhf.pdfrlhf.pdf
rlhf.pdf
ssuserec96e8
 
Adversarial learning for neural dialogue generation
Adversarial learning for neural dialogue generationAdversarial learning for neural dialogue generation
Adversarial learning for neural dialogue generation
Keon Kim
 
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Lionel Briand
 
Text Analytics for Legal work
Text Analytics for Legal workText Analytics for Legal work
Text Analytics for Legal work
AlgoAnalytics Financial Consultancy Pvt. Ltd.
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
IJwest
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
dannyijwest
 

Similar to Improving Neural Question Generation using Answer Separation. (20)

Improving neural question generation using answer separation
Improving neural question generation using answer separationImproving neural question generation using answer separation
Improving neural question generation using answer separation
 
Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...
Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...
Attention-based Models (DLAI D8L 2017 UPC Deep Learning for Artificial Intell...
 
ACL 2018 Recap
ACL 2018 RecapACL 2018 Recap
ACL 2018 Recap
 
Natural Language Generation / Stanford cs224n 2019w lecture 15 Review
Natural Language Generation / Stanford cs224n 2019w lecture 15 ReviewNatural Language Generation / Stanford cs224n 2019w lecture 15 Review
Natural Language Generation / Stanford cs224n 2019w lecture 15 Review
 
Deep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate HelpdeskDeep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate Helpdesk
 
Wecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochureWecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochure
 
Wecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochureWecp all-india-test-series-program-brochure
Wecp all-india-test-series-program-brochure
 
WISS QA Do it yourself Question answering over Linked Data
WISS QA Do it yourself Question answering over Linked DataWISS QA Do it yourself Question answering over Linked Data
WISS QA Do it yourself Question answering over Linked Data
 
American sign language recognizer
American sign language recognizerAmerican sign language recognizer
American sign language recognizer
 
Seminar2017
Seminar2017Seminar2017
Seminar2017
 
Python week 2 2019 2020 for g10 by eng.osama ghandour
Python week 2 2019 2020 for g10 by eng.osama ghandourPython week 2 2019 2020 for g10 by eng.osama ghandour
Python week 2 2019 2020 for g10 by eng.osama ghandour
 
Building a Meta-search Engine
Building a Meta-search EngineBuilding a Meta-search Engine
Building a Meta-search Engine
 
The Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and BeyondThe Frontier of Deep Learning in 2020 and Beyond
The Frontier of Deep Learning in 2020 and Beyond
 
Python week 1 2020-2021
Python week 1 2020-2021Python week 1 2020-2021
Python week 1 2020-2021
 
rlhf.pdf
rlhf.pdfrlhf.pdf
rlhf.pdf
 
Adversarial learning for neural dialogue generation
Adversarial learning for neural dialogue generationAdversarial learning for neural dialogue generation
Adversarial learning for neural dialogue generation
 
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
 
Text Analytics for Legal work
Text Analytics for Legal workText Analytics for Legal work
Text Analytics for Legal work
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
 

Recently uploaded

Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
AbdullaAlAsif1
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
Daniel Tubbenhauer
 
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdfwaterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
LengamoLAppostilic
 
Oedema_types_causes_pathophysiology.pptx
Oedema_types_causes_pathophysiology.pptxOedema_types_causes_pathophysiology.pptx
Oedema_types_causes_pathophysiology.pptx
muralinath2
 
Deep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless ReproducibilityDeep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless Reproducibility
University of Rennes, INSA Rennes, Inria/IRISA, CNRS
 
NuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyerNuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyer
pablovgd
 
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
University of Maribor
 
bordetella pertussis.................................ppt
bordetella pertussis.................................pptbordetella pertussis.................................ppt
bordetella pertussis.................................ppt
kejapriya1
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
Anagha Prasad
 
Eukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptxEukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptx
RitabrataSarkar3
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
MaheshaNanjegowda
 
ESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptxESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptx
PRIYANKA PATEL
 
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
vluwdy49
 
Medical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptxMedical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptx
terusbelajar5
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
İsa Badur
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
HongcNguyn6
 
The binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defectsThe binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defects
Sérgio Sacani
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
KrushnaDarade1
 
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
yqqaatn0
 
Phenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvementPhenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvement
IshaGoswami9
 

Recently uploaded (20)

Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
 
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdfwaterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
 
Oedema_types_causes_pathophysiology.pptx
Oedema_types_causes_pathophysiology.pptxOedema_types_causes_pathophysiology.pptx
Oedema_types_causes_pathophysiology.pptx
 
Deep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless ReproducibilityDeep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless Reproducibility
 
NuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyerNuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyer
 
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
 
bordetella pertussis.................................ppt
bordetella pertussis.................................pptbordetella pertussis.................................ppt
bordetella pertussis.................................ppt
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
 
Eukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptxEukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptx
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
 
ESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptxESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptx
 
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
 
Medical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptxMedical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptx
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
 
The binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defectsThe binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defects
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
 
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
 
Phenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvementPhenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvement
 

Improving Neural Question Generation using Answer Separation.

  • 1. Yanghoon Kim, Hwanhee Lee, Joongbo Shin and Kyomin Jung Improving Neural Question Generation using Answer Separation 김양훈
  • 2. Background Neural question generation (NQG) - Generating a question from a given text passage with deep neural networks. Importance of NQG - Generating questions for educational materials. - Generating questions for improving QA systems. NQG with target Answer - Generating a question from a given text passage and a given target answer(question target) with deep neural networks. 2 Original passage: John Francis O’hara was elected president of Notre Dame in 1934. Generated question 1: Who was elected president of Notre Dame in 1934? Generated question 2: When was John Francis O’hara elected president of Notre Dame?
  • 3. Problem Previous NQG systems suffer from a critical problem - Some models don’t take the target answer into account. - RNNs often follow a shallow generation process. - Some models can’t well grasp the target answer(question target) . - A sophisticated proportion of generated questions include word in the target answer. 3 Original passage: John Francis O’Hara was elected president of Notre Dame in 1934. Given target answer: John Francis O’hara Correctly Generated question: Who was elected president of Notre Dame in 1934? Incorrectly generated question: Who was elected John Francis?
  • 4. Contribution We propose answer-separated seq2seq - Treats the target answer(question target) and the passage separately. - Prevent the generated question from including words in the target answer. - Better capture the information from both the target answer and the passage - We propose keyword-net - Model is consistently aware of the target answer. - Extract the key information in the target answer. - We use retrieval style word generator - Take the word meaning into account when generating words. 4
  • 6. Model Base model - We use RNN encoder-decoder with attention Answer-separated seq2seq consist of - Answer-separated passage encoder - Target answer encoder - Answer-separated decoder - keyword-net - Retrieval style word generator 6
  • 7. Model Answer-separated passage encoder - A simple preprocessing of the input passage - Original passage: Steve Jobs is the founder of Apple. - Masked passage: Steve Jobs is the <a> . - A one-layer bi-LSTM Answer encoder - A one-layer bi-LSTM 7
  • 8. Model Answer-separated decoder - A one-layer LSTM - keyword-net - Let the model consistently be aware of the target answer. - Extract key information. - Passage: Steve Jobs is the founder of Apple - Target answer: founder of Apple 8
  • 9. Model Answer-separated decoder - Retrieval style word generator by (Ma et al. 2018)* - seq2seq has tendency to memorize the sequence pattern rather than reflecting word meanings - The word generator produces words by querying the distributed word representations. *Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation 9
  • 10. Experiment Data - Processed version of SQuAD 1.1 - Data split 1: 70,484/10,570/11,877 (train/dev/test) - Data split 2: 86,635/8,965/8,964 Evaluation Our model(Ass2s) outperform the previous state-of-the-art model 10
  • 11. Experiment Impact of answer separation - Ability to capture target answer - We checked if the target answer is included in the generated question - AP : Answer position Feature (BIO scheme) - (Song et al. 2018) used the copy mechanism. 11 Our model has better ability to generate the right question given the target answer
  • 12. Experiment Impact of answer separation - Interrogative word prediction - “What” takes up more than half of the whole training set - “Which” : “Which year” can be represented as “When” - “why”, “yes/no” : only takes up 1.5% and 1.2% of the training set. 12 Our model has better ability to predict the question type for the given target answer
  • 13. Experiment Impact of answer separation - Attention from <answer> - (a) is the attention matrix from our model - (b) is the attention matrix from seq2seq + AP - <a> token gives the highest attention weights to the interrogative word “who” in (a) 13
  • 14. Experiment Question generation for machine comprehension - Use named entities as target answers, generate synthetic data for machine comprehension system(QA net by Google). - ALL : Evaluation result of SQuAD dev set(10k) - NER : Evaluation result of partial SQuAD dev set(4k) - answers of single named entity 14
  • 15. Conclusion We propose Answer-separated seq2seq for NQG - Separate utilization of target answer and the passage(without target answer) - By masking the target answer inside the passage - By using keyword-net to extract key feature from target answer - By using retrieval style word generator to capture word meaning information - Our model can - Reduce the probability that the target answer is included by the generated question - Generate fluent and right question for the given passage and the target answer - Better inference the type of question
  • 16. Thank you for listening! Code, paper: https://yanghoonkim.github.io Questions: ad26kr@snu.ac.kr