supervised learning of complete morphological paradigms
play

Supervised Learning of Complete Morphological Paradigms Greg - PowerPoint PPT Presentation

Mar 29, 2024 •26 likes •916 views

Supervised Learning of Complete Morphological Paradigms Greg Durrett and John DeNero UC Berkeley / Google Morphological Inflection train (de) Zug Morphological Inflection N OM, S ING: Zug N OM, P LU: Zge train (de) Zug G EN, S ING:

  1. Supervised Learning of Complete Morphological Paradigms Greg Durrett and John DeNero UC Berkeley / Google

  2. Morphological Inflection train (de) Zug

  3. Morphological Inflection N OM, S ING: Zug N OM, P LU: Züge train (de) Zug G EN, S ING: Zuges (8 total) G EN, P LU: Züge ... ...

  4. Morphological Inflection N OM, S ING: Zug N OM, P LU: Züge train (de) Zug G EN, S ING: Zuges (8 total) G EN, P LU: Züge ... ... N OM, S ING: u N OM, P LU: ü u G EN, S ING: u G EN, P LU: ü ... ...

  5. Morphological Inflection N OM, S ING: Zug N OM, P LU: Züge train (de) Zug G EN, S ING: Zuges (8 total) G EN, P LU: Züge ... ... N OM, S ING: u N OM, S ING: g N OM, P LU: ü N OM, P LU: ge u g G EN, S ING: u G EN, S ING: ges G EN, P LU: ü G EN, P LU: ge ... ... ... ...

  6. Morphological Inflection N OM, S ING: Schnellzug N OM, P LU: Schnellzüge express train (de) Schnellzug G EN, S ING: Schnellzuges G EN, P LU: Schnellzüge ... ... N OM, S ING: u N OM, S ING: g N OM, P LU: ü N OM, P LU: ge u g G EN, S ING: u G EN, S ING: ges G EN, P LU: ü G EN, P LU: ge ... ... ... ...

  7. Morphological Inflection N OM, S ING: valkuainen egg white (fi) G EN, S ING: valkuaisen valkuainen P ART, S ING: valkuaista ... ... N OM, S ING: syyllinen culprit (fi) G EN, S ING: syyllisen syyllinen P ART, S ING: syyllistä ... ...

  8. Morphological Inflection N OM, S ING: valkuainen egg white (fi) G EN, S ING: valkuaisen valkuainen P ART, S ING: valkuaista ... ... N OM, S ING: syyllinen culprit (fi) G EN, S ING: syyllisen syyllinen P ART, S ING: syyllistä ... ...

  9. Morphological Inflection N OM, S ING: valkuainen egg white (fi) G EN, S ING: valkuaisen valkuainen P ART, S ING: valkuaista back vowels ... ... N OM, S ING: syyllinen culprit (fi) G EN, S ING: syyllisen syyllinen P ART, S ING: syyllistä ... ...

  10. Morphological Inflection N OM, S ING: valkuainen egg white (fi) G EN, S ING: valkuaisen valkuainen P ART, S ING: valkuaista back vowels ... ... N OM, S ING: syyllinen culprit (fi) G EN, S ING: syyllisen syyllinen P ART, S ING: syyllistä front vowels ... ...

  11. Morphological Inflection N OM, S ING: valkuainen egg white (fi) G EN, S ING: valkuaisen valkuainen P ART, S ING: valkuaista back vowels ... ... N OM, S ING: syyllinen culprit (fi) G EN, S ING: syyllisen syyllinen P ART, S ING: syyllistä front vowels ... ... Suffix morphology can depend on context in a complex way

  12. Morphological Inflection Given Base form (Word)

  13. Morphological Inflection Given Predict Base form Inflection table (variants) (Word) Attributes(1): Inflected form(1) Attributes(2): Inflected form(2) ... ...

  14. Morphological Inflection Given Predict Base form Inflection table (variants) (Word) Attributes(1): Inflected form(1) Attributes(2): Inflected form(2) ... ... Language/POS independence

  15. Morphological Inflection Given Predict Base form Inflection table (variants) (Word) Attributes(1): Inflected form(1) Attributes(2): Inflected form(2) ... ... Language/POS independence Handle multi-part paradigms

  16. Morphological Inflection Given Predict Base form Inflection table (variants) (Word) Attributes(1): Inflected form(1) Attributes(2): Inflected form(2) ... ... Language/POS independence Handle multi-part paradigms Rich way to predict inflections

  17. Outline

  18. Outline Rule extraction (>1000) ... ... Kluft Zug ... ...

  19. Outline Rule extraction (>1000) (<50) ... ... g ... u ... ... Kluft ... Zug ... ...

  20. Outline Rule extraction (>1000) (<50) ... ... g ... u ... ... Kluft ... Zug ... ... Paradigm prediction ( ) ... ... , u Zug ... ...

  21. Outline Rule extraction (>1000) (<50) ... ... g ... u ... ... Kluft ... Zug ... ... Paradigm prediction ( ) Base form ... ... , predictor u Zug ... ... Inflection table

  22. Wiktionary Data Thousands of full inflection tables for many languages and parts of speech

  23. Wiktionary Data Thousands of full inflection tables for many languages and parts of speech http://en.wiktionary.org/wiki/Zug

  24. Wiktionary Data Thousands of full inflection tables for many languages and parts of speech http://en.wiktionary.org/wiki/Zug 2763 more...

  25. Previous Work Dreyer and Eisner (2011) develops a semi- supervised Bayesian model

  26. Previous Work Dreyer and Eisner (2011) develops a semi- supervised Bayesian model Wicentowski (2004) predicts one variant at a time (the lemma)

  27. Previous Work Dreyer and Eisner (2011) develops a semi- supervised Bayesian model Wicentowski (2004) predicts one variant at a time (the lemma) N OM, S ING: u N OM, P LU: ü u G EN, S ING: u G EN, P LU: ü ... ...

  28. Rule Extraction

  29. Rule Extraction 1 P , P RES, S ING: dringe 2 P , P RES, S ING: dringst to insist (de) dringen (27 total) , P RES, S ING: dringt 3 P 1 P , P AST, S ING: drang ... ...

  30. Rule Extraction 1 P , P RES, S ING: dringe 2 P , P RES, S ING: dringst to insist (de) dr i ngen (27 total) , P RES, S ING: dringt 3 P 1 P , P AST, S ING: drang ... ... 1 P , P RES, S ING: i 2 P , P RES, S ING: i i , P RES, S ING: i 3 P 1 P , P AST, S ING: a ... ...

  31. Rule Extraction 1 P , P RES, S ING: dringe 2 P , P RES, S ING: dringst to insist (de) dr i ng en (27 total) , P RES, S ING: dringt 3 P 1 P , P AST, S ING: drang ... ... , P RES, S ING: e 1 P 1 P , P RES, S ING: i 2 P , P RES, S ING: st 2 P , P RES, S ING: i i en , P RES, S ING: t 3 P , P RES, S ING: i 3 P , P AST, S ING: - 1 P 1 P , P AST, S ING: a ... ... ... ...

  32. Alignment to Base Form I NFINITIVE d r i n g e n d r i n g e 1 P , P RES, S ING

  33. Alignment to Base Form I NFINITIVE d r i n g e n D d r i n g e 1 P , P RES, S ING

  34. Alignment to Base Form I NFINITIVE d r i n g e n d r i n g e 1 P , P RES, S ING

  35. Alignment to Base Form I NFINITIVE I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING d r i n g s t 2 P , P RES, S ING

  36. Alignment to Base Form I NFINITIVE I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING S S d r i n g s t 2 P , P RES, S ING

  37. Alignment to Base Form I NFINITIVE d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING

  38. Alignment to Base Form I NFINITIVE I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING S D I NFINITIVE d r i n g e n d r i n g t d r i n g s t 2 P , P RES, S ING 3 P , P RES, S ING

  39. Alignment to Base Form I NFINITIVE d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING

  40. Alignment to Base Form I NFINITIVE I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING S D D I NFINITIVE d r i n g e n d r a n g d r i n g s t 2 P , P RES, S ING 1 P , P AST, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING

  41. Alignment to Base Form I NFINITIVE d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  42. Concatenation I NFINITIVE d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  43. Concatenation I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  44. Concatenation I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  45. Concatenation I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  46. Concatenation I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  47. Concatenation I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  48. Concatenation I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

  49. Concatenation I NFINITIVE d r i n g e n d r i n g e n d r i n g e 1 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g s t 2 P , P RES, S ING I NFINITIVE d r i n g e n d r i n g t 3 P , P RES, S ING I NFINITIVE d r i n g e n d r a n g 1 P , P AST, S ING

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

Discovering Morphological Paradigms from Plain Text Using a

Discovering Morphological Paradigms from Plain Text Using a

Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model Dreyer et al. (2011) Amey Chaugule achaugu2@illinois.edu

372 views • 21 slides
Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model

Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model

Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model Markus Dreyer Jason Eisner SDL Language Weaver Johns Hopkins University This work was done at: Center for Language and Speech Processing (CLSP)

927 views • 89 slides
Learning frameworks Self-supervised learning: (Auto)encoder networks Supervised learning Network

Learning frameworks Self-supervised learning: (Auto)encoder networks Supervised learning Network

Learning frameworks Self-supervised learning: (Auto)encoder networks Supervised learning Network must copy inputs to outputs through Assumes environment specifies correct output (targets) for each input a bottleneck (fewer hidden units)

407 views • 5 slides
Self-Supervised Feature Learning by Learning to Spot Artifacts Wonbin Kim Self-Supervised

Self-Supervised Feature Learning by Learning to Spot Artifacts Wonbin Kim Self-Supervised

Self-Supervised Feature Learning by Learning to Spot Artifacts Wonbin Kim Self-Supervised Learning To exploit different labelings that are freely available besides or within visual data, and to use them as intrinsic reward signals to

387 views • 24 slides
Stacking for supervised learning Stacking for supervised learning Niall Rooney, NIKEL,

Stacking for supervised learning Stacking for supervised learning Niall Rooney, NIKEL,

Stacking for supervised learning Stacking for supervised learning Niall Rooney, NIKEL, University of Ulster 1 Ensemble learning Ensemble learning l Postulate multiple hypotheses to explain the data l Shortcomings of single model learning

681 views • 19 slides
Machine Learning for NLP Supervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Supervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Supervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain Sciences University of Trento 1 Supervised learning Supervised: you know the result of the task you want to perform. Supervised learning mostly

832 views • 61 slides
PCA CS 446 Supervised learning So far, weve done supervised learning: Given (( x i , y i )) ,

PCA CS 446 Supervised learning So far, weve done supervised learning: Given (( x i , y i )) ,

PCA CS 446 Supervised learning So far, weve done supervised learning: Given (( x i , y i )) , find f with f ( x i ) y i . k -nn, decision trees, . . . 1 / 18 Supervised learning So far, weve done supervised learning: Given (( x i , y

1.01k views • 56 slides
Semi-Supervised Learning Maria-Florina Balcan 03/30/2015 Readings: Semi-Supervised Learning.

Semi-Supervised Learning Maria-Florina Balcan 03/30/2015 Readings: Semi-Supervised Learning.

Semi-Supervised Learning Maria-Florina Balcan 03/30/2015 Readings: Semi-Supervised Learning. Encyclopedia of Machine Learning. Jerry Zhu, 2010 Combining Labeled and Unlabeled Data with Co- Training. Avrim Blum, Tom Mitchell. COLT

953 views • 45 slides
RECSM Summer School: Machine Learning for Social Sciences Session 1.3: Supervised Learning and

RECSM Summer School: Machine Learning for Social Sciences Session 1.3: Supervised Learning and

RECSM Summer School: Machine Learning for Social Sciences Session 1.3: Supervised Learning and Model Accuracy Reto West Department of Political Science and International Relations University of Geneva 1 Supervised Learning Supervised

436 views • 42 slides
CSE 158 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression

CSE 158 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression

CSE 158 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression What is supervised learning? Supervised learning is the process of trying to infer from labeled data the underlying function that produced the labels

751 views • 25 slides
CSE 158 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression

CSE 158 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression

CSE 158 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression What is supervised learning? Supervised learning is the process of trying to infer from labeled data the underlying function that produced the labels

784 views • 33 slides
CSE 258 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression

CSE 258 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression

CSE 258 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression What is supervised learning? Supervised learning is the process of trying to infer from labeled data the underlying function that produced the labels

599 views • 33 slides
Machine Learning Lecture 6 Unsupervised Learning with a bit of Supervised Learning Clustering

Machine Learning Lecture 6 Unsupervised Learning with a bit of Supervised Learning Clustering

Machine Learning Lecture 6 Unsupervised Learning with a bit of Supervised Learning Clustering and nearest neighbour classifiers. Justin Pearson 1 2020 1 http://user.it.uu.se/~justin/Teaching/MachineLearning/index.html 1 / 27 Supervised

813 views • 27 slides
Web Mining and Recommender Systems Supervised learning Regression Learning Goals Introduce

Web Mining and Recommender Systems Supervised learning Regression Learning Goals Introduce

Web Mining and Recommender Systems Supervised learning Regression Learning Goals Introduce the concept of Supervised Learning Understand the components (inputs and outputs) of supervised learning problems Introduce linear

1.36k views • 122 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
THE SUPERVISED LEARNING PROBLEM THE SUPERVISED LEARNING PROBLEM Matthieu R Bloch January 7, 2020

THE SUPERVISED LEARNING PROBLEM THE SUPERVISED LEARNING PROBLEM Matthieu R Bloch January 7, 2020

THE SUPERVISED LEARNING PROBLEM THE SUPERVISED LEARNING PROBLEM Matthieu R Bloch January 7, 2020 1 WHY ML ? WHY ML ? Traditional engineering is top-down We use fundamental principles (mathematics, physics) to build models and abstractions

243 views • 13 slides
Managing many models February 2016 Hadley Wickham @hadleywickham Chief Scientist,

Managing many models February 2016 Hadley Wickham @hadleywickham Chief Scientist,

Managing many models February 2016 Hadley Wickham @hadleywickham Chief Scientist, RStudio There are 7 key components of data science Import Visualise Communicate Transform Tidy Automate Model Understand Today I want to focus

683 views • 43 slides
A CUCKOOS EGG IN THE MALWARE NEST ON-THE-FLY SIGNATURE-LESS MALWARE ANALYSIS, DETECTION AND

A CUCKOOS EGG IN THE MALWARE NEST ON-THE-FLY SIGNATURE-LESS MALWARE ANALYSIS, DETECTION AND

A CUCKOOS EGG IN THE MALWARE NEST ON-THE-FLY SIGNATURE-LESS MALWARE ANALYSIS, DETECTION AND CONTAINMENT FOR LARGE NETWORKS CHRISTIAAN SCHADE TWENTE SECURITY LAB UNIVERSITY OF TWENTE THE NETHERLANDS MALWARE WARS In the last

313 views • 14 slides
17: Dynamic Programming CS1101S: Programming Methodology Martin Henz October 19, 2012 CS1101S:

17: Dynamic Programming CS1101S: Programming Methodology Martin Henz October 19, 2012 CS1101S:

Fibonacci Numbers Dropping Eggs Puzzle Optimal Binary Search Tree 17: Dynamic Programming CS1101S: Programming Methodology Martin Henz October 19, 2012 CS1101S: Programming Methodology 17: Dynamic Programming Fibonacci Numbers Dropping

660 views • 25 slides
The joy of functional programming June 2019 Hadley Wickham @hadleywickham Chief

The joy of functional programming June 2019 Hadley Wickham @hadleywickham Chief

The joy of functional programming June 2019 Hadley Wickham @hadleywickham Chief Scientist, RStudio Import Visualise Tidy Transform Model Program Communicate Import Visualise Tidy Transform Model Program Communicate

445 views • 42 slides
Parsing Contexts Context Sensitive Grammars for Everyone Jan Kur kurs@iam.unibe.ch Software

Parsing Contexts Context Sensitive Grammars for Everyone Jan Kur kurs@iam.unibe.ch Software

Parsing Contexts Context Sensitive Grammars for Everyone Jan Kur kurs@iam.unibe.ch Software Composition Group Indentation using Petit Parser print Hello! if keyword if (outOf(milk)): print We are out of milk! block of commands

576 views • 57 slides
women participating in the Nutrition Links Project in a rural district of Ghana Afua

women participating in the Nutrition Links Project in a rural district of Ghana Afua

Poultry egg production and utilization among NUTRITION LINKS women participating in the Nutrition Links Project in a rural district of Ghana Afua Atuobi-Yeboah, Grace Marquis, Esi Colecraft, Frances Aboud, Shelley Clark, Theresa Gyorkos,

486 views • 25 slides
Basic Data Mining Algorithms Liyao Xiang http://xiangliyao.cn/ Shanghai Jiao Tong University

Basic Data Mining Algorithms Liyao Xiang http://xiangliyao.cn/ Shanghai Jiao Tong University

EE226 Big Data Mining Lecture 3 Basic Data Mining Algorithms Liyao Xiang http://xiangliyao.cn/ Shanghai Jiao Tong University http://jhc.sjtu.edu.cn/public/courses/EE226/ Notice There will be a quiz in the next weeks class. Please take a

363 views • 15 slides
Crisis Management SE in the USA Bob Krouse Midwest Poultry Services April 5, 2011 Agenda What

Crisis Management SE in the USA Bob Krouse Midwest Poultry Services April 5, 2011 Agenda What

Crisis Management SE in the USA Bob Krouse Midwest Poultry Services April 5, 2011 Agenda What Happened What We Did Results New Egg Safety Rule July 9, 2010 Industry Prepared for Potential Crisis: Established roles and

838 views • 39 slides

More recommend