folktale classification using learning to rank
play

Folktale Classification using Learning to Rank Dong Nguyen, Dolf - PowerPoint PPT Presentation

Oct 21, 2023 •250 likes •625 views

Folktale Classification using Learning to Rank Dong Nguyen, Dolf Trieschnigg, and Marit Theune University of Twente Folktales Fairy tales Riddles Legends Urban legends Jokes Etc.. Folktale researchers Folktales

  1. Folktale Classification using Learning to Rank Dong Nguyen, Dolf Trieschnigg, and Mariët Theune University of Twente

  6. Folktales • Fairy tales • Riddles • Legends • Urban legends • Jokes • Etc..

  7. Folktale researchers • Folktales are a resource to research – Variation in tales – Shifting moral values, beliefs, identities etc. – Intertextuality

  8. Classification systems • Folktale researchers have developed classification systems • To compare and analyze stories • To organize stories

  9. Classification systems • Folktale researchers have developed classification systems • To compare and analyze stories • To organize stories Story types ¡

  10. The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. �

  11. A car driver picks up a hitchhiker. They talk about spiritual topics in life. � Suddenly the hitchhiker vanishes. The police tell � him they have heard the � story earlier that day. � The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. �

  12. A car driver picks up a A guy bikes through the park � hitchhiker. They talk about at night. He encounters a � spiritual topics in life. � girl covered in blood. � Suddenly the hitchhiker On their way to the � vanishes. The police tell � police, she suddenly � him they have heard the � disappears. She resembles a story earlier that day. � murdered girl… � The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. �

  13. A car driver picks up a A guy bikes through the park � hitchhiker. They talk about at night. He encounters a � spiritual topics in life. � girl covered in blood. � Suddenly the hitchhiker On their way to the � vanishes. The police tell � police, she suddenly � him they have heard the � disappears. She resembles a story earlier that day. � murdered girl… � The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. � A car driver picks up a hitchhiker and borrows her � his sweater. When he stops � by to pick up the sweater, � he discovers she passed � away due to a car accident � a while ago. He finds � his sweater on her grave. �

  14. A car driver picks up a A guy bikes through the park � hitchhiker. They talk about at night. He encounters a � spiritual topics in life. � girl covered in blood. � Suddenly the hitchhiker On their way to the � vanishes. The police tell � police, she suddenly � him they have heard the � disappears. She resembles a story earlier that day. � murdered girl… � The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. � A car driver picks up a A car driver picks up a girl hitchhiker and borrows her � wearing a white dress. He his sweater. When he stops � accidently spills red wine on by to pick up the sweater, � her dress. The next day � he discovers she passed � he finds out she died a � away due to a car accident � year ago. When the police open � a while ago. He finds � her grave, they find the white � his sweater on her grave. � dress with the red wine spot. �

  15. A car driver picks up a A guy bikes through the park � hitchhiker. They talk about at night. He encounters a � spiritual topics in life. � girl covered in blood. � Suddenly the hitchhiker On their way to the � vanishes. The police tell � police, she suddenly � him they have heard the � disappears. She resembles a story earlier that day. � murdered girl … � The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. � A car driver picks up a A car driver picks up a girl hitchhiker and borrows her � wearing a white dress. He his sweater. When he stops � accidently spills red wine on by to pick up the sweater, � her dress. The next day � he discovers she passed � he finds out she died a � away due to a car accident � year ago . When the police open � a while ago. He finds � her grave, they find the white � his sweater on her grave. � dress with the red wine spot. �

  16. A car driver picks up a A guy bikes through the park � hitchhiker. They talk about at night. He encounters a � spiritual topics in life. � girl covered in blood. � Suddenly the hitchhiker On their way to the � vanishes. The police tell � police, she suddenly � him they have heard the � disappears. She resembles a story earlier that day. � murdered girl… � The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. � A car driver picks up a A car driver picks up a girl hitchhiker and borrows her � wearing a white dress. He his sweater. When he stops � accidently spills red wine on by to pick up the sweater, � her dress. The next day � he discovers she passed � he finds out she died a � away due to a car accident � year ago. When the police open � a while ago. He finds � her grave, they find the white � his sweater on her grave. � dress with the red wine spot. �

  17. A car driver picks up a A guy bikes through the park � hitchhiker. They talk about at night. He encounters a � spiritual topics in life. � girl covered in blood. � Suddenly the hitchhiker On their way to the � vanishes. The police tell � police, she suddenly � him they have heard the � disappears. She resembles a story earlier that day. � murdered girl… � The Vanishing Hitchhiker (BRUN 01000) � � A ghostly or heavenly hitchhiker that vanishes � from a vehicle, sometimes after giving warning or prophecy. � A car driver picks up a A car driver picks up a girl hitchhiker and borrows her � wearing a white dress . He his sweater. When he stops � accidently spills red wine on by to pick up the sweater , � her dress. The next day � he discovers she passed � he finds out she died a � away due to a car accident � year ago. When the police open � a while ago. He finds � her grave, they find the white � his sweater on her grave. � dress with the red wine spot. �

  18. Story Type Indexes: ATU Aarne-­‑Thompson-­‑Uther ¡ ¡ classifica4on ¡system ¡(ATU) ¡ ¡ Red ¡Riding ¡Hood ¡ ¡(ATU ¡0333), ¡ ¡ The ¡Race ¡between ¡Hare ¡and ¡ Tortoise ¡ (ATU ¡0275A), ¡etc.

  19. Story Type Indexes: Brunvand Urban ¡legends ¡ ¡ The ¡Microwaved ¡Pet ¡(BRUN ¡02000), ¡ The ¡Kidney ¡Heist ¡(BRUN ¡06305), ¡ ¡ The ¡Killer ¡in ¡the ¡Backseat ¡ ¡ ¡ ¡ ¡(BRUN ¡01305), ¡ ¡ The ¡Vanishing ¡Hitchhiker ¡ ¡ ¡ ¡ ¡ ¡(BRUN ¡01000), ¡ etc.

  20. Automatic Identification of Story Types • Increasing digitalization • Discover relationships between stories

  21. Outline • Problem ¡descrip4on, ¡corpora ¡ • Experimental ¡setup ¡ – Baselines, ¡Learning ¡to ¡Rank ¡ ¡ • Results ¡ – Baselines, ¡Feature ¡analysis, ¡Error ¡analysis ¡ • Discussion/Conclusion ¡

  22. Goal and Evaluation Given an input story, return a ranking of story types 1 • Semi automatic setting ¡Reciprocal ¡Rank ¡(MRR) ¡ rank i ¡ • Classifica4on ¡ – Simula4ng ¡a ¡classifica4on ¡seRng. ¡The ¡highest ¡ranked ¡ label ¡is ¡then ¡taken ¡as ¡the ¡predicted ¡class. ¡ ¡ ¡A ccuracy

  23. Folktale database • Dutch Folktale Database (http://www.verhalenbank.nl) • Over 42.000 stories • In our experiments: only stories written in standard Dutch

  24. Dataset I Number of storytypes Number of storytypes 60 60 40 40 20 20 0 0 0 20 40 60 0 20 40 60 Number of stories Number of stories (a) ATU (b) Brunvand Fig. 1. Story type frequencies

  25. Dataset II Index ¡ Train ¡ Dev ¡ Test ¡ Nr ¡documents ¡ 400 ¡ ¡ 75 ¡ ¡ 25 ¡ 50 ¡ Nr ¡story ¡types ¡ 98 ¡ 59 ¡ ¡ 24 ¡ 43 ¡ ATU ¡ Index ¡ Train ¡ Dev ¡ Test ¡ Nr ¡documents ¡ 687 ¡ ¡ 175 ¡ 50 ¡ 75 ¡ Nr ¡story ¡types ¡ 125 ¡ ¡ 92 ¡ 40 ¡ 50 ¡ Brunvand ¡

  26. Baselines: big doc Input ¡document ¡(query) ¡ Vanishing ¡ Hitchiker ¡ ¡ Killer ¡in ¡the ¡ Backseat ¡ Microwaved ¡ ¡ Pet ¡ Ranking ¡ Killer ¡in ¡the ¡ Backseat ¡

  27. Baselines: small doc Input ¡document ¡(query) ¡ Vanishing ¡ Hitchiker ¡ Vanishing ¡ Hitchiker ¡ Microwaved ¡ Pet ¡ Killer ¡in ¡the ¡ Microwaved ¡ Backseat ¡ Pet ¡ Ranking ¡ Killer ¡in ¡the ¡ Backseat ¡ When ¡taking ¡the ¡top ¡ranked ¡label ¡as ¡the ¡class, ¡ ¡this ¡is ¡the ¡same ¡as ¡a ¡Nearest ¡Neighbour ¡classifier ¡(k=1). ¡ ¡

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Learning to Extract Folktale Keywords Dolf Trieschnigg, Dong

Learning to Extract Folktale Keywords Dolf Trieschnigg, Dong

Folktales As Classifiable Texts Learning to Extract Folktale Keywords Dolf Trieschnigg, Dong Nguyen and Marit Theune Once upon a time There was

421 views • 23 slides
10. Learning to Rank Outline 10.1. Why Learning to Rank (LeToR)? 10.2. Pointwise, Pairwise,

10. Learning to Rank Outline 10.1. Why Learning to Rank (LeToR)? 10.2. Pointwise, Pairwise,

10. Learning to Rank Outline 10.1. Why Learning to Rank (LeToR)? 10.2. Pointwise, Pairwise, Listwise 10.3. Gathering User Input 10.4. LeToR Evaluation 10.5. Beyond Search Advanced Topics in Information Retrieval / Learning to Rank 2 10.1.

1.01k views • 34 slides
Folktales and Fables Folktale traditional stories that have been passed down from one generation

Folktales and Fables Folktale traditional stories that have been passed down from one generation

Folktales and Fables Folktale traditional stories that have been passed down from one generation to the next by being told aloud. No matter what culture they came from, folktales usually have similar characteristics. Elements of a Folktale

192 views • 8 slides
2 3 4 5 8 9 MINNEAPOLIS MILWAUKEE MSA RANK #16 MSA RANK #39 CHICAGO MSA RANK #3

2 3 4 5 8 9 MINNEAPOLIS MILWAUKEE MSA RANK #16 MSA RANK #39 CHICAGO MSA RANK #3

2 3 4 5 8 9 MINNEAPOLIS MILWAUKEE MSA RANK #16 MSA RANK #39 CHICAGO MSA RANK #3 INDIANAPOLIS MSA RANK #34 DETROIT MSA RANK #14 COLUMBUS MSA RANK #33 BALTIMORE/ DC CORRIDOR MSA RANK #21 CINCINNATI MSA RANK #28 ATLANTA MSA RANK

726 views • 44 slides
Learning to Rank Learning to Rank with Partially-Labeled Data with Partially-Labeled Data Kevin

Learning to Rank Learning to Rank with Partially-Labeled Data with Partially-Labeled Data Kevin

Learning to Rank Learning to Rank with Partially-Labeled Data with Partially-Labeled Data Kevin Duh University of Washington (Joint work with Katrin Kirchhoff) 1 Motivation Motivation Machine learning can be an effective solution for

472 views • 29 slides
Introduction to Information Retrieval http://informationretrieval.org IIR 15-2: Learning to Rank

Introduction to Information Retrieval http://informationretrieval.org IIR 15-2: Learning to Rank

Machine-learned relevance Learning to rank Introduction to Information Retrieval http://informationretrieval.org IIR 15-2: Learning to Rank Hinrich Sch utze Institute for Natural Language Processing, Universit at Stuttgart 2011-08-29

1.3k views • 115 slides
A classification of self-dual codes with a rank 3 automorphism group of almost simple type

A classification of self-dual codes with a rank 3 automorphism group of almost simple type

A classification of self-dual codes with a rank 3 automorphism group of almost simple type Bernardo Rodrigues School of Mathematics, Statistics and Computer Science University of KwaZulu-Natal Durban, South Africa Groups St Andrews 2017

413 views • 30 slides
Learning to Rank with Learning to Rank with Partially-Labeled Data Partially-Labeled Data Kevin

Learning to Rank with Learning to Rank with Partially-Labeled Data Partially-Labeled Data Kevin

Learning to Rank with Learning to Rank with Partially-Labeled Data Partially-Labeled Data Kevin Duh University of Washington 1 The Ranking Problem The Ranking Problem Definition: Given a set of objects, sort them by preference. objectA

716 views • 59 slides
Online Learning to Rank with Features Authors: Shuai Li, Tor Lattimore, Csaba Szepesvri The

Online Learning to Rank with Features Authors: Shuai Li, Tor Lattimore, Csaba Szepesvri The

Online Learning to Rank with Features Authors: Shuai Li, Tor Lattimore, Csaba Szepesvri The Chinese University of Hong Kong DeepMind University of Alberta Learning to Rank Amazon, YouTube, Facebook, Netflix, Taobao 1 Online Learning to

530 views • 17 slides
Cross-Domain Learning-to-rank with SVM Erheng Zhong 1 1 Department of Computer Science and

Cross-Domain Learning-to-rank with SVM Erheng Zhong 1 1 Department of Computer Science and

Preliminary Cross-domain Learning-to-Rank Summary Cross-Domain Learning-to-rank with SVM Erheng Zhong 1 1 Department of Computer Science and Technology, HKUST COMP621U Presentation, 04/07/2011 Erheng Zhong Cross-Domain Learning-to-rank

620 views • 40 slides
1 Similarity ranking: example Weighted scoring with linear combination A simple weighted

1 Similarity ranking: example Weighted scoring with linear combination A simple weighted

Table of Content Weighted scoring for ranking Learning to rank: A simple example Learning to ranking as classification Ranking and Learning 290N UCSB, Tao Yang, 2013 Partially based on Manning, Raghavan, and Schtzes text book.

476 views • 8 slides
Decision Rule-based Algorithm for Ordinal Classification based on Rank Loss Minimization

Decision Rule-based Algorithm for Ordinal Classification based on Rank Loss Minimization

Decision Rule-based Algorithm for Ordinal Classification based on Rank Loss Minimization Krzysztof Dembczyski 1 , 2 , Wojciech Kotowski 1 , 3 1 Institute of Computing Science, Pozna University of Technology 2 KEBI, Philipps-Universit at

419 views • 30 slides
Learning to rank search results Voting algorithms, rank combination methods Web Search Andr

Learning to rank search results Voting algorithms, rank combination methods Web Search Andr

Learning to rank search results Voting algorithms, rank combination methods Web Search Andr Mouro, Joo Magalhes 1 2 How can we merge these results? Which model should we select for our production system? Not trivial. Would

616 views • 40 slides
Rank-Based Classification of Gene Expression Profiles Daniel Q. Naiman Collaborators: Donald

Rank-Based Classification of Gene Expression Profiles Daniel Q. Naiman Collaborators: Donald

Rank-Based Classification of Gene Expression Profiles Daniel Q. Naiman Collaborators: Donald Geman , Christian dAvignon & Raimond L. Winslow Department of Applied Mathematics and Statistics Center for

295 views • 28 slides
Weakly Supervised Classification Weakly Supervised Classification and Robust Learning and Robust

Weakly Supervised Classification Weakly Supervised Classification and Robust Learning and Robust

IIT-H and RIKEN-AIP Joint Workshop on March 15, 2019 Machine Learning and Applications, Hyderabad, India Weakly Supervised Classification Weakly Supervised Classification and Robust Learning and Robust Learning --- Overview of Our Recent

1.06k views • 25 slides
Controlling Fairness and Bias in Dynamic Learning-to-Rank ACM SIGIR 2020 Marco Morik * ,

Controlling Fairness and Bias in Dynamic Learning-to-Rank ACM SIGIR 2020 Marco Morik * ,

Controlling Fairness and Bias in Dynamic Learning-to-Rank ACM SIGIR 2020 Marco Morik * , Ashudeep Singh * , Jessica Hong , Thorsten Joachims TU Berlin, Cornell University Dynamic Learning-to-Rank +1 +1 +1 +1 +1 1 2

224 views • 20 slides
2 Related Work Figure 1. Training and Test Instances. Most existing work on associative

2 Related Work Figure 1. Training and Test Instances. Most existing work on associative

Lazy Associative Classification Adriano Veloso a , Wagner Meira Jr. a , Mohammed J. Zaki b a Computer Science Dept, Federal University of Minas Gerais, Brazil b Computer Science Dept, Rensselaer Polytechnic Institute, Troy, USA { adrianov,meira

448 views • 10 slides
The Evolution of BC Liquor Laws Legal Issues Affecting the BC Wine Industry Mark Hicken,

The Evolution of BC Liquor Laws Legal Issues Affecting the BC Wine Industry Mark Hicken,

The Evolution of BC Liquor Laws Legal Issues Affecting the BC Wine Industry Mark Hicken, Vintage Law Group November 2018. Penticton, BC Introduction Liquor Regulation in BC - Have to Trace Back to Prohibition Uniquely North

357 views • 20 slides
M ichigan Petroleum Storage Tank Conference October 23, 2019 STEVE GAL VAN Sr. Field M

M ichigan Petroleum Storage Tank Conference October 23, 2019 STEVE GAL VAN Sr. Field M

WEIGHTS AND M EASURES PROGRAM M ichigan Petroleum Storage Tank Conference October 23, 2019 STEVE GAL VAN Sr. Field M etrologist and Presenter RYANNE HARTM AN Weights and M easures Specialist and Service Registration Administrator

375 views • 16 slides
3 P R O D U C T I O N M E T H O D S A range of glasses that suit any budget and occasion

3 P R O D U C T I O N M E T H O D S A range of glasses that suit any budget and occasion

3 P R O D U C T I O N M E T H O D S A range of glasses that suit any budget and occasion Consistent shape and design across all manufacturing methods HANDMADE MACHINE MADE OUTDOORS European Crystal European Crystal Durable polycarbonate C

71 views • 6 slides
Rules and Regulations Compliance, Inspection & Certification Bill Gibson Consultant Marine

Rules and Regulations Compliance, Inspection & Certification Bill Gibson Consultant Marine

Superyacht Rules and Regulations Compliance, Inspection & Certification Bill Gibson Consultant Marine Engineer 2018 Super Yacht Compliance & Certification ITC Tonnage Measurements Class Society Rules SOLAS

427 views • 39 slides
Napa County Travel Behavior Study NCTPA Board Meeting Presentation December 17, 2014 1 Overview

Napa County Travel Behavior Study NCTPA Board Meeting Presentation December 17, 2014 1 Overview

Napa County Travel Behavior Study NCTPA Board Meeting Presentation December 17, 2014 1 Overview Objectives of the Study Community Advisory Committee Study Approach Data Analysis and Integration Conclusions 2 Objectives of the

382 views • 25 slides
Explaining the result of a Decision Tree to the End-User Isabelle Alvarez 1 2 Abstract. This

Explaining the result of a Decision Tree to the End-User Isabelle Alvarez 1 2 Abstract. This

Explaining the result of a Decision Tree to the End-User Isabelle Alvarez 1 2 Abstract. This paper addresses the problem of the explanation of tests that are in the trace can have no consequences on the result. the result given by a decision

548 views • 6 slides
Regional Workshop Workshop Purpose To increase RCA understanding of what it will take to Purpose

Regional Workshop Workshop Purpose To increase RCA understanding of what it will take to Purpose

Regional Workshop Workshop Purpose To increase RCA understanding of what it will take to Purpose Purpose develop a business case approach activity management plan (BCA AMP) and how using ONRC data can help inform decision making. Overview

862 views • 62 slides

More recommend