狠狠撸

狠狠撸Share a Scribd company logo
LEARNING BY ANALOGY IN
A HYBRID ONTOLOGICAL
NETWORK
Ponomarev S. V.
ponomarev@corp.sputnik.ru
?Sputnik?
The Hybrid Ontological Network
We call an ontology hybrid if:
1. It is composed of several independent sources;
2. It contains triplets (links), accumulated in statistical text corpora
processing;
3. Each triplet characterized by type and weight.
The main properties of this ontology are redundancy and high relatedness.
Redundancy arises from the duplication of most ontological links in
various used sources, and high relatedness arises in inclusion of links
obtained by statistical text processing.
Nodes: 1.4 mil.
Links: 639 mil.
Link Types: 64
Network sample
1 link 3 links
1 * 3 = 3 paths from tomato to color trough red
Tomato
Link types: 23
Red
Link types : 22
Color
Link types : 30
The link structure between the vertices:
"TOMATO", "RED", "COLOR"
Building a path between the vertices:
"TOMATO", "RED", "COLOR"
Applying constructed path in the network
To build a path in the hybrid network, you should specify a set of pairs
"link type – link weight”:
START >> (-22, 1) >> RESULT;
FINISH >> (8, 1/3) >> RESULT;
FINISH >> (-22, 1/3) >> RESULT;
FINISH >> (-25, 1/3) >> RESULT.
The link structure through one
intermediate vertice
QA System. Step 1
The rule base is empty, so random response generated. A pair of
"question - answer" memorized.
Question: Какой глубины лужа? (What depth is the puddle?)
Correct Answer: Лужа - мелкая. (The puddle is small)
Generated Answer: Глубина. (Depth)
New Rule Added.
QA System. Step 2
In the rule base there’s the only rule obtained in step 1, and the system
tries to apply this rule to the question. Attempt fails and the rule is
corrected.
Question: Какой глубины море? (What depth is the sea?)
Correct Answer: Море - глубокое. (The sea is deep)
Generated Answer: Море - мелкое. (The sea is small)
Adding 1 New Path.
QA System. Step 3
In the rule base there’s still the only rule, but it’s taught at two examples.
The system makes a successful attempt to apply this rule to the
question. Thus, in this case two training examples are enough to
obtain practically valuable rule.
Question: Какой глубины океан? (What depth is the ocean?)
Correct Answer: Океан - глубокий. (The ocean is deep)
Generated Answer: Океан - глубокий.
(The ocean is deep)Correct Answer Found.
QA System. Step 4
The syntactic structure of pair "question - answer" is changed, so the
use of the existing rule does not give the correct result. Another rule
is generated.
Question: Какой глубины лужа? (What depth is the puddle?)
Correct Answer: Лужа маленькой глубины. (The puddle is small depth)
Generated Answer: Лужа - мелкая. (The puddle is small)
Generated Answer: Глубина. (Depth)
New Rule Added.
QA System. Step 5
Attempt to apply rule № 2, obtained in step 4, gives the correct result
within meaning, but not coinciding exactly with the correct answer.
Rule № 2 is corrected.
Question: Какой глубины море? (What depth is the sea?)
Correct Answer: Море большой глубины. (The sea is deep depth)
Generated Answer: Море огромной глубины. (The sea is vast depth)
Adding 1 New Path.
QA System. Step 6
The syntactic structure of pair "question - answer" corresponds more
with the rule № 2, than with the rule №1. The attempt to apply rule
№2 to determine the color instead of the size gives the expected
result.
Question: Какого цвета огурец? (What color is the cucumber?)
Correct Answer: Огурец зеленого цвета. (The cucumber is green color)
Generated Answer: Огурец зеленого цвета. (The cucumber is green
color)
Correct Answer Found.
The structure of rule №2
Thank you
Ponomarev S. V.
ponomarev@corp.sputnik.ru
?Sputnik?
Ad

Recommended

LEARNING BY ANALOGY IN A HYBRID ONTOLOGICAL NETWORK
LEARNING BY ANALOGY IN A HYBRID ONTOLOGICAL NETWORK
Сергей Пономарев
?
Pruning cooccurrence networks
Pruning cooccurrence networks
Raf Guns
?
Carmine gelormini network analysis
Carmine gelormini network analysis
CarmineGelormini
?
Конкурс Родная речь 2014
Конкурс Родная речь 2014
Сергей Пономарев
?
Автоматическая голосовая служба поддержки
Автоматическая голосовая служба поддержки
Сергей Пономарев
?
Перефразировщик текста
Перефразировщик текста
Сергей Пономарев
?
Технологический стек классификации текстов на естественных языках
Технологический стек классификации текстов на естественных языках
Сергей Пономарев
?
Word2vec для поискового движка II
Word2vec для поискового движка II
Сергей Пономарев
?
Классификация текстовых документов на естественных языках
Классификация текстовых документов на естественных языках
Сергей Пономарев
?
Semantic evaluation on Dialog 2015
Semantic evaluation on Dialog 2015
Сергей Пономарев
?
ПОСТРОЕНИЕ ОТНОШЕНИЙ В СМЕШАННОЙ ОНТОЛОГИЧЕСКОЙ СЕТИ ДЛЯ РЕШЕНИЯ ЗАДАЧ ТЕСТИР...
ПОСТРОЕНИЕ ОТНОШЕНИЙ В СМЕШАННОЙ ОНТОЛОГИЧЕСКОЙ СЕТИ ДЛЯ РЕШЕНИЯ ЗАДАЧ ТЕСТИР...
Сергей Пономарев
?
Классификация поисковых запросов
Классификация поисковых запросов
Сергей Пономарев
?
Word2vec для поискового движка
Word2vec для поискового движка
Сергей Пономарев
?
Концепция поисковых расширений
Концепция поисковых расширений
Сергей Пономарев
?
reporting monthly for genset & Air Compressor.pptx
reporting monthly for genset & Air Compressor.pptx
dacripapanjaitan
?
Presentation by Tariq & Mohammed (1).pptx
Presentation by Tariq & Mohammed (1).pptx
AbooddSandoqaa
?
lecture12.pdf Introduction to bioinformatics
lecture12.pdf Introduction to bioinformatics
SergeyTsygankov6
?
最新版美国约翰霍普金斯大学毕业证(闯贬鲍毕业证书)原版定制
最新版美国约翰霍普金斯大学毕业证(闯贬鲍毕业证书)原版定制
Taqyea
?
Communication_Skills_Class10_Visual.pptx
Communication_Skills_Class10_Visual.pptx
namanrastogi70555
?
The Influence off Flexible Work Policies
The Influence off Flexible Work Policies
sales480687
?
定制翱颁础顿学生卡加拿大安大略艺术与设计大学成绩单范本,翱颁础顿成绩单复刻
定制翱颁础顿学生卡加拿大安大略艺术与设计大学成绩单范本,翱颁础顿成绩单复刻
taqyed
?
Lesson-3_Program-Outcomes-and-Student-Learning-Outcomes_For-Students.pdf
Lesson-3_Program-Outcomes-and-Student-Learning-Outcomes_For-Students.pdf
SarahMaeDuallo
?
最新版美国芝加哥大学毕业证(鲍颁丑颈肠补驳辞毕业证书)原版定制
最新版美国芝加哥大学毕业证(鲍颁丑颈肠补驳辞毕业证书)原版定制
taqyea
?
一比一原版(罢鲍颁毕业证书)开姆尼茨工业大学毕业证如何办理
一比一原版(罢鲍颁毕业证书)开姆尼茨工业大学毕业证如何办理
taqyed
?
最新版美国威斯康星大学河城分校毕业证(鲍奥搁贵毕业证书)原版定制
最新版美国威斯康星大学河城分校毕业证(鲍奥搁贵毕业证书)原版定制
taqyea
?
PPT2 W1L2.pptx.........................................
PPT2 W1L2.pptx.........................................
palicteronalyn26
?
最新版美国佐治亚大学毕业证(鲍骋础毕业证书)原版定制
最新版美国佐治亚大学毕业证(鲍骋础毕业证书)原版定制
Taqyea
?
Boost Business Efficiency with Professional Data Entry Services
Boost Business Efficiency with Professional Data Entry Services
eloiacs eloiacs
?
Attendance Presentation Project Excel.pptx
Attendance Presentation Project Excel.pptx
s2025266191
?
美国毕业证范本中华盛顿大学学位证书颁奥鲍学生卡购买
美国毕业证范本中华盛顿大学学位证书颁奥鲍学生卡购买
Taqyea
?

More Related Content

More from Сергей Пономарев (6)

Классификация текстовых документов на естественных языках
Классификация текстовых документов на естественных языках
Сергей Пономарев
?
Semantic evaluation on Dialog 2015
Semantic evaluation on Dialog 2015
Сергей Пономарев
?
ПОСТРОЕНИЕ ОТНОШЕНИЙ В СМЕШАННОЙ ОНТОЛОГИЧЕСКОЙ СЕТИ ДЛЯ РЕШЕНИЯ ЗАДАЧ ТЕСТИР...
ПОСТРОЕНИЕ ОТНОШЕНИЙ В СМЕШАННОЙ ОНТОЛОГИЧЕСКОЙ СЕТИ ДЛЯ РЕШЕНИЯ ЗАДАЧ ТЕСТИР...
Сергей Пономарев
?
Классификация поисковых запросов
Классификация поисковых запросов
Сергей Пономарев
?
Word2vec для поискового движка
Word2vec для поискового движка
Сергей Пономарев
?
Концепция поисковых расширений
Концепция поисковых расширений
Сергей Пономарев
?
Классификация текстовых документов на естественных языках
Классификация текстовых документов на естественных языках
Сергей Пономарев
?
ПОСТРОЕНИЕ ОТНОШЕНИЙ В СМЕШАННОЙ ОНТОЛОГИЧЕСКОЙ СЕТИ ДЛЯ РЕШЕНИЯ ЗАДАЧ ТЕСТИР...
ПОСТРОЕНИЕ ОТНОШЕНИЙ В СМЕШАННОЙ ОНТОЛОГИЧЕСКОЙ СЕТИ ДЛЯ РЕШЕНИЯ ЗАДАЧ ТЕСТИР...
Сергей Пономарев
?
Классификация поисковых запросов
Классификация поисковых запросов
Сергей Пономарев
?

Recently uploaded (20)

reporting monthly for genset & Air Compressor.pptx
reporting monthly for genset & Air Compressor.pptx
dacripapanjaitan
?
Presentation by Tariq & Mohammed (1).pptx
Presentation by Tariq & Mohammed (1).pptx
AbooddSandoqaa
?
lecture12.pdf Introduction to bioinformatics
lecture12.pdf Introduction to bioinformatics
SergeyTsygankov6
?
最新版美国约翰霍普金斯大学毕业证(闯贬鲍毕业证书)原版定制
最新版美国约翰霍普金斯大学毕业证(闯贬鲍毕业证书)原版定制
Taqyea
?
Communication_Skills_Class10_Visual.pptx
Communication_Skills_Class10_Visual.pptx
namanrastogi70555
?
The Influence off Flexible Work Policies
The Influence off Flexible Work Policies
sales480687
?
定制翱颁础顿学生卡加拿大安大略艺术与设计大学成绩单范本,翱颁础顿成绩单复刻
定制翱颁础顿学生卡加拿大安大略艺术与设计大学成绩单范本,翱颁础顿成绩单复刻
taqyed
?
Lesson-3_Program-Outcomes-and-Student-Learning-Outcomes_For-Students.pdf
Lesson-3_Program-Outcomes-and-Student-Learning-Outcomes_For-Students.pdf
SarahMaeDuallo
?
最新版美国芝加哥大学毕业证(鲍颁丑颈肠补驳辞毕业证书)原版定制
最新版美国芝加哥大学毕业证(鲍颁丑颈肠补驳辞毕业证书)原版定制
taqyea
?
一比一原版(罢鲍颁毕业证书)开姆尼茨工业大学毕业证如何办理
一比一原版(罢鲍颁毕业证书)开姆尼茨工业大学毕业证如何办理
taqyed
?
最新版美国威斯康星大学河城分校毕业证(鲍奥搁贵毕业证书)原版定制
最新版美国威斯康星大学河城分校毕业证(鲍奥搁贵毕业证书)原版定制
taqyea
?
PPT2 W1L2.pptx.........................................
PPT2 W1L2.pptx.........................................
palicteronalyn26
?
最新版美国佐治亚大学毕业证(鲍骋础毕业证书)原版定制
最新版美国佐治亚大学毕业证(鲍骋础毕业证书)原版定制
Taqyea
?
Boost Business Efficiency with Professional Data Entry Services
Boost Business Efficiency with Professional Data Entry Services
eloiacs eloiacs
?
Attendance Presentation Project Excel.pptx
Attendance Presentation Project Excel.pptx
s2025266191
?
美国毕业证范本中华盛顿大学学位证书颁奥鲍学生卡购买
美国毕业证范本中华盛顿大学学位证书颁奥鲍学生卡购买
Taqyea
?
Crafting-Research-Recommendations Grade 12.pptx
Crafting-Research-Recommendations Grade 12.pptx
DaryllWhere
?
Starbucks in the Indian market through its joint venture.
Starbucks in the Indian market through its joint venture.
sales480687
?
@Reset-Password.pptx presentakh;kenvtion
@Reset-Password.pptx presentakh;kenvtion
MarkLariosa1
?
Indigo dyeing Presentation (2).pptx as dye
Indigo dyeing Presentation (2).pptx as dye
shreeroop1335
?
reporting monthly for genset & Air Compressor.pptx
reporting monthly for genset & Air Compressor.pptx
dacripapanjaitan
?
Presentation by Tariq & Mohammed (1).pptx
Presentation by Tariq & Mohammed (1).pptx
AbooddSandoqaa
?
lecture12.pdf Introduction to bioinformatics
lecture12.pdf Introduction to bioinformatics
SergeyTsygankov6
?
最新版美国约翰霍普金斯大学毕业证(闯贬鲍毕业证书)原版定制
最新版美国约翰霍普金斯大学毕业证(闯贬鲍毕业证书)原版定制
Taqyea
?
Communication_Skills_Class10_Visual.pptx
Communication_Skills_Class10_Visual.pptx
namanrastogi70555
?
The Influence off Flexible Work Policies
The Influence off Flexible Work Policies
sales480687
?
定制翱颁础顿学生卡加拿大安大略艺术与设计大学成绩单范本,翱颁础顿成绩单复刻
定制翱颁础顿学生卡加拿大安大略艺术与设计大学成绩单范本,翱颁础顿成绩单复刻
taqyed
?
Lesson-3_Program-Outcomes-and-Student-Learning-Outcomes_For-Students.pdf
Lesson-3_Program-Outcomes-and-Student-Learning-Outcomes_For-Students.pdf
SarahMaeDuallo
?
最新版美国芝加哥大学毕业证(鲍颁丑颈肠补驳辞毕业证书)原版定制
最新版美国芝加哥大学毕业证(鲍颁丑颈肠补驳辞毕业证书)原版定制
taqyea
?
一比一原版(罢鲍颁毕业证书)开姆尼茨工业大学毕业证如何办理
一比一原版(罢鲍颁毕业证书)开姆尼茨工业大学毕业证如何办理
taqyed
?
最新版美国威斯康星大学河城分校毕业证(鲍奥搁贵毕业证书)原版定制
最新版美国威斯康星大学河城分校毕业证(鲍奥搁贵毕业证书)原版定制
taqyea
?
PPT2 W1L2.pptx.........................................
PPT2 W1L2.pptx.........................................
palicteronalyn26
?
最新版美国佐治亚大学毕业证(鲍骋础毕业证书)原版定制
最新版美国佐治亚大学毕业证(鲍骋础毕业证书)原版定制
Taqyea
?
Boost Business Efficiency with Professional Data Entry Services
Boost Business Efficiency with Professional Data Entry Services
eloiacs eloiacs
?
Attendance Presentation Project Excel.pptx
Attendance Presentation Project Excel.pptx
s2025266191
?
美国毕业证范本中华盛顿大学学位证书颁奥鲍学生卡购买
美国毕业证范本中华盛顿大学学位证书颁奥鲍学生卡购买
Taqyea
?
Crafting-Research-Recommendations Grade 12.pptx
Crafting-Research-Recommendations Grade 12.pptx
DaryllWhere
?
Starbucks in the Indian market through its joint venture.
Starbucks in the Indian market through its joint venture.
sales480687
?
@Reset-Password.pptx presentakh;kenvtion
@Reset-Password.pptx presentakh;kenvtion
MarkLariosa1
?
Indigo dyeing Presentation (2).pptx as dye
Indigo dyeing Presentation (2).pptx as dye
shreeroop1335
?
Ad

Learning by Analogy

  • 1. LEARNING BY ANALOGY IN A HYBRID ONTOLOGICAL NETWORK Ponomarev S. V. ponomarev@corp.sputnik.ru ?Sputnik?
  • 2. The Hybrid Ontological Network We call an ontology hybrid if: 1. It is composed of several independent sources; 2. It contains triplets (links), accumulated in statistical text corpora processing; 3. Each triplet characterized by type and weight. The main properties of this ontology are redundancy and high relatedness. Redundancy arises from the duplication of most ontological links in various used sources, and high relatedness arises in inclusion of links obtained by statistical text processing. Nodes: 1.4 mil. Links: 639 mil. Link Types: 64
  • 3. Network sample 1 link 3 links 1 * 3 = 3 paths from tomato to color trough red Tomato Link types: 23 Red Link types : 22 Color Link types : 30
  • 4. The link structure between the vertices: "TOMATO", "RED", "COLOR"
  • 5. Building a path between the vertices: "TOMATO", "RED", "COLOR"
  • 6. Applying constructed path in the network To build a path in the hybrid network, you should specify a set of pairs "link type – link weight”: START >> (-22, 1) >> RESULT; FINISH >> (8, 1/3) >> RESULT; FINISH >> (-22, 1/3) >> RESULT; FINISH >> (-25, 1/3) >> RESULT.
  • 7. The link structure through one intermediate vertice
  • 8. QA System. Step 1 The rule base is empty, so random response generated. A pair of "question - answer" memorized. Question: Какой глубины лужа? (What depth is the puddle?) Correct Answer: Лужа - мелкая. (The puddle is small) Generated Answer: Глубина. (Depth) New Rule Added.
  • 9. QA System. Step 2 In the rule base there’s the only rule obtained in step 1, and the system tries to apply this rule to the question. Attempt fails and the rule is corrected. Question: Какой глубины море? (What depth is the sea?) Correct Answer: Море - глубокое. (The sea is deep) Generated Answer: Море - мелкое. (The sea is small) Adding 1 New Path.
  • 10. QA System. Step 3 In the rule base there’s still the only rule, but it’s taught at two examples. The system makes a successful attempt to apply this rule to the question. Thus, in this case two training examples are enough to obtain practically valuable rule. Question: Какой глубины океан? (What depth is the ocean?) Correct Answer: Океан - глубокий. (The ocean is deep) Generated Answer: Океан - глубокий. (The ocean is deep)Correct Answer Found.
  • 11. QA System. Step 4 The syntactic structure of pair "question - answer" is changed, so the use of the existing rule does not give the correct result. Another rule is generated. Question: Какой глубины лужа? (What depth is the puddle?) Correct Answer: Лужа маленькой глубины. (The puddle is small depth) Generated Answer: Лужа - мелкая. (The puddle is small) Generated Answer: Глубина. (Depth) New Rule Added.
  • 12. QA System. Step 5 Attempt to apply rule № 2, obtained in step 4, gives the correct result within meaning, but not coinciding exactly with the correct answer. Rule № 2 is corrected. Question: Какой глубины море? (What depth is the sea?) Correct Answer: Море большой глубины. (The sea is deep depth) Generated Answer: Море огромной глубины. (The sea is vast depth) Adding 1 New Path.
  • 13. QA System. Step 6 The syntactic structure of pair "question - answer" corresponds more with the rule № 2, than with the rule №1. The attempt to apply rule №2 to determine the color instead of the size gives the expected result. Question: Какого цвета огурец? (What color is the cucumber?) Correct Answer: Огурец зеленого цвета. (The cucumber is green color) Generated Answer: Огурец зеленого цвета. (The cucumber is green color) Correct Answer Found.
  • 14. The structure of rule №2
  • 15. Thank you Ponomarev S. V. ponomarev@corp.sputnik.ru ?Sputnik?