using support vector machines and state of the art
play

Using support vector machines and state-of-the-art algorithms for - PowerPoint PPT Presentation

Nov 27, 2023 •371 likes •886 views

Using support vector machines and state-of-the-art algorithms for phonetic alignment to identify cognates in multi-lingual wordlists Gerhard Jger, Johann-Mattis List & Pavel Sofroniev Tbingen University & MPI Jena

  1. Using support vector machines and state-of-the-art algorithms for phonetic alignment to identify cognates in multi-lingual wordlists Gerhard Jäger¹, Johann-Mattis List² & Pavel Sofroniev¹ ¹Tübingen University & ²MPI Jena Valencia, EACL 2017 April 7, 2017 Jäger, List & Sofroniev (Tübingen/Jena) Automatic cognate detection EACL2017 1 / 23

  2. Introduction Computational historical linguistics EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) ... patterns in language change discovery of statistical proto-languages automatic reconstruction of families homeland of language inferring time depth and classifjcation automated language 15 years massive progress within past 2 / 23 (Grollemund et al, 2015) (Bouckaert et al, 2012)

  3. Introduction Computational historical linguistics most work depends on manually coded cognate judgments on Swadesh lists labor intensive subjective not fully replicable induces bias in favor of well-studied language families Jäger, List & Sofroniev (Tübingen/Jena) Automatic cognate detection EACL2017 3 / 23

  4. Introduction Cognate-coded word lists typical data structure in CHL goal of this talk: How to automatically infer cognate classifjcation. Jäger, List & Sofroniev (Tübingen/Jena) Automatic cognate detection EACL2017 4 / 23

  5. Previous Work Previous Work EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 5 / 23 слово слово λόγος word Wort Wort cuvînt cuvînt palabra palabra mot mot adottszó adottszó slovo slovo verbum verbum word focal focal 词 词 parola parola λόγος word शब◌् शब◌् द द ord ord ord ord

  6. Previous Work Previous Work EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 5 / 23 ID T axa Word Gloss GlossID IPA ..... ... ... ... ... ... ... ... 21 German Frau woman 20 frau ... 22 Dutch vrouw woman 20 vrɑu ... 23 English woman woman 20 wʊmən ... 24 Danish kvinde woman 20 kvenə ... 25 Swedish kvinna woman 20 kviːna ... 26 Norwegian kvine woman 20 kʋinə ... ... ... ... ... ... ... ...

  7. Previous Work Previous Work EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 5 / 23 ID T axa Word Gloss GlossID IPA CogID ... ... ... ... ... ... ... 21 German Frau woman 20 frau 1 22 Dutch vrouw woman 20 vrɑu 1 23 English woman woman 20 wʊmən 2 24 Danish kvinde woman 20 kvenə 3 25 Swedish kvinna woman 20 kviːna 3 26 Norwegian kvine woman 20 kʋinə 3 ... ... ... ... ... ... ...

  8. Previous Work Previous Work EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 5 / 23 ID T axa Word Gloss GlossID IPA CogID ... ... ... ... ... ... ... 21 German Frau woman 20 frau 1 22 Dutch vrouw woman 20 vrɑu 1 23 English woman woman 20 wʊmən 2 24 Danish kvinde woman 20 kvenə 3 25 Swedish kvinna woman 20 kviːna 3 26 Norwegian kvine woman 20 kʋinə 3 ... ... ... ... ... ... ...

  9. Previous Work Previous Work: Sound Classes Sound Classes Sounds which often occur in correspondence relations in genetically related languages can be clustered into classes (types). It is assumed “that phonetic correspondences inside a ‘type’ are more regular than those between difgerent ‘types’” (Dolgopolsky 1986: 35). Jäger, List & Sofroniev (Tübingen/Jena) Automatic cognate detection EACL2017 6 / 23

  10. Previous Work Previous Work: Sound Classes Sound Classes Sounds which often occur in correspondence relations in genetically related languages can be clustered into classes (types). It is assumed “that phonetic correspondences inside a ‘type’ are more regular than those between difgerent ‘types’” (Dolgopolsky 1986: 35). Jäger, List & Sofroniev (Tübingen/Jena) Automatic cognate detection EACL2017 6 / 23

  11. Previous Work more regular than those between EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) Previous Work: Sound Classes 35). difgerent ‘types’” (Dolgopolsky 1986: 6 / 23 correspondences inside a ‘type’ are assumed “that phonetic clustered into classes (types). It is genetically related languages can be Sound Classes Sounds which often occur in correspondence relations in g p k b ʧ ʤ v f ʒ ʃ t d s z θ ð 1

  12. Previous Work more regular than those between EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) Previous Work: Sound Classes 35). difgerent ‘types’” (Dolgopolsky 1986: 6 / 23 correspondences inside a ‘type’ are assumed “that phonetic clustered into classes (types). It is genetically related languages can be Sound Classes Sounds which often occur in correspondence relations in g p k b ʧ ʤ v f ʒ ʃ t d s z θ ð 1

  13. Previous Work more regular than those between EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) Previous Work: Sound Classes 35). difgerent ‘types’” (Dolgopolsky 1986: 6 / 23 correspondences inside a ‘type’ are assumed “that phonetic clustered into classes (types). It is genetically related languages can be Sound Classes Sounds which often occur in correspondence relations in g p k b ʧ ʤ v f ʒ ʃ t d s z θ ð 1

  14. Previous Work more regular than those between EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 35). Previous Work: Sound Classes difgerent ‘types’” (Dolgopolsky 1986: correspondences inside a ‘type’ are assumed “that phonetic clustered into classes (types). It is genetically related languages can be correspondence relations in Sounds which often occur in Sound Classes 6 / 23 K P T S 1

  15. Previous Work more regular than those between EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) Previous Work: Sound Classes 35). difgerent ‘types’” (Dolgopolsky 1986: 6 / 23 correspondences inside a ‘type’ are genetically related languages can be clustered into classes (types). It is Sound Classes Sounds which often occur in correspondence relations in assumed “that phonetic the to approach according is usually based on comparing the fjrst two K P (CCM) consonants of two words: If they match regarding identifjcation Matching their sound classes, the words are judged to be Cognate Consonant-Class cognate, otherwise not. T S 1

  16. Previous Work Previous Work: Alignment-Based Approaches EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 7 / 23 PAIRWISE WORDLIST DATA COMPARISON PAIRWISE COGNATE DISTANCES CLUSTERING BETWEEN WORDS COGNATE SETS

  17. Previous Work Previous Work: Alignment-Based Approaches EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 7 / 23 ID Taxa Word Gloss GlossID IPA Analysis ... ... ... ... ... ... 21 German Frau woman 20 frau 22 Dutch vrouw woman 20 vr ɑ u 23 English woman woman 20 w ʊ m ə n 24 Danish kvinde woman 20 kven ə 25 Swedish kvinna woman 20 kvi ː na 26 Norwegian kvine woman 20 k ʋ in ə ... ... ... ... ... ...

  18. Previous Work Previous Work: Alignment-Based Approaches EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 7 / 23 ID Taxa Word Gloss GlossID IPA Analysis ... ... ... ... ... ... 21 German Frau woman 20 frau 22 Dutch vrouw woman 20 vr ɑ u 23 English woman woman 20 w ʊ m ə n 24 Danish kvinde woman 20 kven ə 25 Swedish kvinna woman 20 kvi ː na 26 Norwegian kvine woman 20 k ʋ in ə ... ... ... ... ... ... Swedish English Danish Norwegian Dutch German kvinna woman kvinde kvine vrouw Frau Swedish 0.00 0.69 0.07 0.12 0.71 0.78 kvina English 0.69 0.00 0.66 0.57 0.68 0.87 wumin Danish 0.07 0.66 0.00 0.08 0.67 0.71 kveni Norwegian 0.12 0.57 0.08 0.00 0.75 0.74 kwini Dutch 0.71 0.68 0.67 0.75 0.00 0.17 frou German 0.78 0.87 0.71 0.74 0.17 0.00 frau

  19. Previous Work Previous Work: Alignment-Based Approaches EACL2017 Automatic cognate detection Jäger, List & Sofroniev (Tübingen/Jena) 7 / 23 Swedish English Danish Norwegian Dutch German kvinna woman kvinde kvine vrouw Frau Swedish 0.00 0.69 0.07 0.12 0.71 0.78 kvina English 0.69 0.00 0.66 0.57 0.68 0.87 wumin Danish 0.07 0.66 0.00 0.08 0.67 0.71 kveni Norwegian 0.12 0.57 0.08 0.00 0.75 0.74 kwini Dutch 0.71 0.68 0.67 0.75 0.00 0.17 frou German 0.78 0.87 0.71 0.74 0.17 0.00 frau German Frau frau Dutch vrouw vrou English woman wumin Danish kvinde kveni Swedish kvinna kvina Norwegian kvine kwini

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

? 17.10.2018 3 17.10.2018 4 Support Vector Machines (SVM): Background Support Vector Machines

? 17.10.2018 3 17.10.2018 4 Support Vector Machines (SVM): Background Support Vector Machines

INF3490 - Biologically inspired computing Support Vector Machines Support Vector Machines, Ensemble Learning, and Dimensionality (SVM) Reduction Weria Khaksar October 17, 2018 17.10.2018 2 Support Vector Machines (SVM): Background Support

579 views • 9 slides
Support Vector Machines (Ch. 18.9) SVM Basics Support Vector Machines (SVMs) try to do our

Support Vector Machines (Ch. 18.9) SVM Basics Support Vector Machines (SVMs) try to do our

Support Vector Machines (Ch. 18.9) SVM Basics Support Vector Machines (SVMs) try to do our normal linear classification (last few lectures), but with a couple of twists 1. Find the line in the middle of points with the largest gap (called

454 views • 32 slides
Support Vector Machines October 16, 2018 Support Vector Machines October 16, 2018 1 / 31

Support Vector Machines October 16, 2018 Support Vector Machines October 16, 2018 1 / 31

Support Vector Machines October 16, 2018 Support Vector Machines October 16, 2018 1 / 31 Introduction General information support vector machine (SVM) is an approach for classification that was developed in the computer science community in

654 views • 27 slides
Support Vector Machines 290N, 2014 Support Vector Machines (SVM) Supervised learning

Support Vector Machines 290N, 2014 Support Vector Machines (SVM) Supervised learning

Support Vector Machines 290N, 2014 Support Vector Machines (SVM) Supervised learning methods for classification and regression they can represent non-linear functions and they have an efficient training algorithm derived

1.15k views • 57 slides
Support Vector Machines Support Vector Machines CSC 411 Tutorial April 1, 2015 Tutor: Shenlong

Support Vector Machines Support Vector Machines CSC 411 Tutorial April 1, 2015 Tutor: Shenlong

Support Vector Machines Support Vector Machines CSC 411 Tutorial April 1, 2015 Tutor: Shenlong Wang Many thanks to Renjie Liao, Jake Snell, Yujia Li and Kevin Swersky for much of the following material. 1 of 36 2 of 36 Brief Review of SVMs

762 views • 36 slides
What is a What are Support Vector Machines Support Vector Machine? Used For? An optimally

What is a What are Support Vector Machines Support Vector Machine? Used For? An optimally

What is a What are Support Vector Machines Support Vector Machine? Used For? An optimally defined surface Classification Typically nonlinear in the input space Regression and data-fitting Linear in a higher dimensional

577 views • 8 slides
Support Vector Machines Preview What is a support vector machine? The perceptron revisited

Support Vector Machines Preview What is a support vector machine? The perceptron revisited

Support Vector Machines Preview What is a support vector machine? The perceptron revisited Kernels Weight optimization Handling noisy data What Is a Support Vector Machine? 1. A subset of the training examples x (the support

971 views • 19 slides
Kernel Machines Steven J Zeil Old Dominion Univ. Fall 2010 1 Support Vector Machines Kernel

Kernel Machines Steven J Zeil Old Dominion Univ. Fall 2010 1 Support Vector Machines Kernel

Support Vector Machines Kernel Machines Kernel Machines Steven J Zeil Old Dominion Univ. Fall 2010 1 Support Vector Machines Kernel Machines Kernel Machines Support Vector Machines 1 Optimal Separating HyperPlanes Soft Margin

368 views • 36 slides
Support Vector Machines & Kernelization Barna Saha Most of the slides are made using David

Support Vector Machines & Kernelization Barna Saha Most of the slides are made using David

Support Vector Machines & Kernelization Barna Saha Most of the slides are made using David Sontags course on machine Learning at MIT Support Vector Machines Support Vector Machines What if the data is not linearly separable?

341 views • 23 slides
Introduction Kailash Awati Instructor DataCamp Support Vector Machines in R Preliminaries

Introduction Kailash Awati Instructor DataCamp Support Vector Machines in R Preliminaries

DataCamp Support Vector Machines in R SUPPORT VECTOR MACHINES IN R Introduction Kailash Awati Instructor DataCamp Support Vector Machines in R Preliminaries Objective : gain understanding of how SVMs work; options available in the algorithm

1.25k views • 22 slides
SUPPORT VECTOR MACHINES SUPPORT VECTOR MACHINES Matthieu R Bloch Tuesday, February 25, 2020 1

SUPPORT VECTOR MACHINES SUPPORT VECTOR MACHINES Matthieu R Bloch Tuesday, February 25, 2020 1

SUPPORT VECTOR MACHINES SUPPORT VECTOR MACHINES Matthieu R Bloch Tuesday, February 25, 2020 1 LOGISTICS LOGISTICS TAs and Office hours Tuesday: Dr. Bloch (College of Architecture Cafe) - 11am - 11:55am Tuesday: TJ (VL C449 Cubicle D) -

467 views • 13 slides
Kernel Machines Support Vector Machines 1 Kernel Machines Optimal Separating HyperPlanes Soft

Kernel Machines Support Vector Machines 1 Kernel Machines Optimal Separating HyperPlanes Soft

Support Vector Machines Kernel Machines Support Vector Machines Kernel Machines Kernel Machines Support Vector Machines 1 Kernel Machines Optimal Separating HyperPlanes Soft Margin HyperPlanes Steven J Zeil Kernel Machines 2 Old

655 views • 8 slides
Gender Classification with Support vector machines (SVMs) Support Vector Machines The 3

Gender Classification with Support vector machines (SVMs) Support Vector Machines The 3

Readings Supervised object recognition, Brief overview of classifiers in context of gender recognition: unsupervised object recognition http://www.merl.com/reports/docs/TR2000-01.pdf, Gender Classification with Support Vector Machines

548 views • 20 slides
RBF Kernels: Generating a complex dataset DataCamp Support Vector Machines in R A bit about RBF

RBF Kernels: Generating a complex dataset DataCamp Support Vector Machines in R A bit about RBF

DataCamp Support Vector Machines in R SUPPORT VECTOR MACHINES IN R RBF Kernels: Generating a complex dataset DataCamp Support Vector Machines in R A bit about RBF Kernels Highly flexible kernel. Can fit complex decision boundaries. Commonly

467 views • 27 slides
Support Vector Machines This set of notes presents the Support Vector Machine (SVM) learning al-

Support Vector Machines This set of notes presents the Support Vector Machine (SVM) learning al-

CS229 Lecture notes Andrew Ng Part V Support Vector Machines This set of notes presents the Support Vector Machine (SVM) learning al- gorithm. SVMs are among the best (and many believe are indeed the best) off-the-shelf supervised

563 views • 25 slides
Machine Learning for NLP Support Vector Machines Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Support Vector Machines Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Support Vector Machines Aurlie Herbelot 2019 Centre for Mind/Brain Sciences University of Trento 1 Support Vector Machines: introduction 2 Support Vector Machines (SVMs) SVMs are supervised algorithms for

1.04k views • 57 slides
Antecedent and referent types of abstract pronominal anaphora Costanza Navarretta University of

Antecedent and referent types of abstract pronominal anaphora Costanza Navarretta University of

Centre for Language Technology Antecedent and referent types of abstract pronominal anaphora Costanza Navarretta University of Copenhagen costanza@hum.ku.dk Beyond Semantics, Gttingen February 23-25 2011 Centre for Language Technology

593 views • 22 slides
Cellularity and the Jones basic construction Cellularity definition Ponidicherry Conference,

Cellularity and the Jones basic construction Cellularity definition Ponidicherry Conference,

Cellularity and the Jones basic construction Frederick Goodman Introduction The Jones basic construction Cellularity and the Jones basic construction Cellularity definition Ponidicherry Conference, 2010 weaker, better definition basis

330 views • 31 slides
Morphological and Part-of-Speech Tagging of Historical Language Data: A Comparison Stefanie

Morphological and Part-of-Speech Tagging of Historical Language Data: A Comparison Stefanie

Morphological and Part-of-Speech Tagging of Historical Language Data: A Comparison Stefanie Dipper Linguistics Department Ruhr-University Bochum 5 January, 2012 Workshop on Annotation of Corpora for Research in the Humanities Heidelberg

994 views • 60 slides
Context 1. Observation (before light pollution) 2. Explanation 3. Model Phaenomena " the

Context 1. Observation (before light pollution) 2. Explanation 3. Model Phaenomena " the

Context 1. Observation (before light pollution) 2. Explanation 3. Model Phaenomena " the things that appear " regular, observable patterns explanation and model: geometric mechanism cause? Observations Time-lapse photograph:

423 views • 19 slides
Tutorial Outline Tutorial Outline XLE: XLE: What is a deep grammar and why would you want

Tutorial Outline Tutorial Outline XLE: XLE: What is a deep grammar and why would you want

Tutorial Outline Tutorial Outline XLE: XLE: What is a deep grammar and why would you want Grammar Development Platform Grammar Development Platform one? Parser/Generator XLE: A First Walkthrough Parser/Generator Robustness

495 views • 34 slides
The Tokai to Kamioka Long Baseline Neutrino Oscillation Experiment An image of the first beam

The Tokai to Kamioka Long Baseline Neutrino Oscillation Experiment An image of the first beam

The Tokai to Kamioka Long Baseline Neutrino Oscillation Experiment An image of the first beam neutrino event candidate seen at Super-Kamiokande M Scott, Imperial College London 1 Overview Theory of neutrino oscillations Experiment

398 views • 15 slides
Evaluating Answers to Reading Results for German and the Role of Comprehension Questions in

Evaluating Answers to Reading Results for German and the Role of Comprehension Questions in

Evaluating Answers to RC Questions in Context: Evaluating Answers to Reading Results for German and the Role of Comprehension Questions in Context: Information Structure Detmar Meurers, Ramon Ziai, Niels Ott, Janina Kopp Results for German

578 views • 31 slides
Modular Springer Correspondence for classical groups Karine Sorlin Universit e de Picardie

Modular Springer Correspondence for classical groups Karine Sorlin Universit e de Picardie

Modular Springer Correspondence for classical groups Modular Springer Correspondence for classical groups Karine Sorlin Universit e de Picardie Jules Verne 13th March, 2012 Modular Springer Correspondence for classical groups Introduction

890 views • 60 slides

More recommend