learning sentence planning rules with bayesian methods
play

Learning Sentence Planning Rules with Bayesian Methods David M. - PowerPoint PPT Presentation

Aug 17, 2022 •177 likes •878 views

Learning Sentence Planning Rules with Bayesian Methods David M. Howcroft Department of Language Science and Technology Saarland Informatics Campus, Saarland University, Germany 24 October 2018 Howcroft (UdS) Learning Sentence Planning 24 Oct

  1. Learning Sentence Planning Rules with Bayesian Methods David M. Howcroft Department of Language Science and Technology Saarland Informatics Campus, Saarland University, Germany 24 October 2018 Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 1 / 23

  2. Natural Language Generation How do we transform non-linguistic input ... name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood ...into a natural language text ? Due Fratelli is an Italian restaurant, while Andalucia is a Spanish seafood restaurant. However, Due Fratelli’s price is average, while Andalucia’s price is more expensive. Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 2 / 23

  3. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  4. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Simplest case: use templates! Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  5. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Simplest case: use templates! inform(NAME, CUISINE) Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  6. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Simplest case: use templates! inform(NAME, CUISINE) → “NAME is a CUISINE restaurant” Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  7. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Simplest case: use templates! inform(NAME, CUISINE) → “NAME is a CUISINE restaurant” → “NAME serves CUISINE food” Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  8. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Simplest case: use templates! inform(NAME, CUISINE) → “NAME is a CUISINE restaurant” → “NAME serves CUISINE food” But this doesn’t generalize; only good for limited applications! Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  9. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Simplest case: use templates! inform(NAME, CUISINE) → “NAME is a CUISINE restaurant” → “NAME serves CUISINE food” But this doesn’t generalize; only good for limited applications! Solution : modularity for reusability Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  10. Templates and traditional approaches to NLG name price cuisine Due Fratelli $$ Italian Andalucia $$$ Spanish, Seafood Simplest case: use templates! inform(NAME, CUISINE) → “NAME is a CUISINE restaurant” → “NAME serves CUISINE food” But this doesn’t generalize; only good for limited applications! Solution : modularity for reusability ◮ Factor out language-general elements Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 3 / 23

  11. ‘The’ NLG Pipeline Meaning Representation (MR): Text Planning Content Selection DB records, slot-value pairs, etc Document Structuring Sentence Planning Lexicalization Aggregation Referring Expres- sion Generation Surface Realization Linearization Morphosyntactic Agreement Punctuation & Natural Language Text Capitalization More reusable components, but still requires a lot of human attention. Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 4 / 23

  12. End-to-end machine learning approaches to NLG Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  13. End-to-end machine learning approaches to NLG Represent meanings as collections of slot-value pairs... Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  14. End-to-end machine learning approaches to NLG Represent meanings as collections of slot-value pairs... inform(name=DueFratelli, cuisine=Italian) inform(name=Andalucia, cuisine=Spanish,Seafood) Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  15. End-to-end machine learning approaches to NLG Represent meanings as collections of slot-value pairs... inform(name=DueFratelli, cuisine=Italian) inform(name=Andalucia, cuisine=Spanish,Seafood) Represent texts as sequences of words... Due Fratelli serves Italian food. Andalucia is a Spanish, seafood restaurant. Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  16. End-to-end machine learning approaches to NLG Represent meanings as collections of slot-value pairs... inform(name=DueFratelli, cuisine=Italian) inform(name=Andalucia, cuisine=Spanish,Seafood) Represent texts as sequences of words... Due Fratelli serves Italian food. Andalucia is a Spanish, seafood restaurant. Apply your favorite sequence-to-sequence model Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  17. End-to-end machine learning approaches to NLG Represent meanings as collections of slot-value pairs... inform(name=DueFratelli, cuisine=Italian) inform(name=Andalucia, cuisine=Spanish,Seafood) Represent texts as sequences of words... Due Fratelli serves Italian food. Andalucia is a Spanish, seafood restaurant. Apply your favorite sequence-to-sequence model ◮ Bayesian networks for gen. w/active learning (Mairesse et al. 2010; BAGEL) Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  18. End-to-end machine learning approaches to NLG Represent meanings as collections of slot-value pairs... inform(name=DueFratelli, cuisine=Italian) inform(name=Andalucia, cuisine=Spanish,Seafood) Represent texts as sequences of words... Due Fratelli serves Italian food. Andalucia is a Spanish, seafood restaurant. Apply your favorite sequence-to-sequence model ◮ Bayesian networks for gen. w/active learning (Mairesse et al. 2010; BAGEL) ◮ Semantically-Conditioned LSTM (Wen et al. 2015) ◮ TGen (Dušek & Jurčíček 2016) ◮ Neural Checklist Model (Kiddon et al. 2016) Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  19. End-to-end machine learning approaches to NLG Represent meanings as collections of slot-value pairs... inform(name=DueFratelli, cuisine=Italian) inform(name=Andalucia, cuisine=Spanish,Seafood) Represent texts as sequences of words... Due Fratelli serves Italian food. Andalucia is a Spanish, seafood restaurant. Apply your favorite sequence-to-sequence model ◮ Bayesian networks for gen. w/active learning (Mairesse et al. 2010; BAGEL) ◮ Semantically-Conditioned LSTM (Wen et al. 2015) ◮ TGen (Dušek & Jurčíček 2016) ◮ Neural Checklist Model (Kiddon et al. 2016) Problem : shallow representations and relative opacity Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 5 / 23

  20. Can we have the best of both worlds? From the rule-based approach: ◮ existing resources for NLG; ◮ richer semantic & syntactic structure; ◮ inspectability; and ◮ modularity where it’s helpful. From the ML approach: ◮ reduced development effort Let’s find out! Narrowing our focus: ◮ assume text planning already done ◮ learn sentence planning rules ◮ use existing systems for surface realization Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 6 / 23

  21. Text Plans with Discourse Structure Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 7 / 23

  22. Text Plans with Discourse Structure Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 7 / 23

  23. Text Plans with Discourse Structure Due Fratelli is an Italian restaurant, while Andalucia is a Spanish seafood restaurant. However, Due Fratelli’s price is average, while Andalucia’s price is more expensive. Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 7 / 23

  24. Morphosyntactic Reps for Surface Realization Text Plan ‘Logical Form’ be contrast 0 1 A M g g r r Arg1 o r g A A 2 d price price price dollar while Arg1 1 Arg2 A g Mod r Det r g A Arg1 2 the at 51 be SoniaRose 51 Bienvenue 35 Arg0 Arg1 Arg1 Sonia Rose price dollar Mod Det Arg1 the at 35 ◮ OpenCCG for surface realization Arg1 ◮ morphosyntactic rep: logical forms Bienvenue ◮ think ‘lemmatized dependency trees’ ◮ based on CCGbank (Hockenmaier 2006) = ⇒ WSJ coverage Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 8 / 23

  25. How to represent tree-to-tree mappings? Synchronous Tree Substitution Grammars contrast but 1 A Next First g r r g A 2 be be price price Arg1 Arg2 1 A Arg0 Arg1 Arg0 Arg1 g r r g A 2 price dollar price dollar SoniaRose 51 Bienvenue 35 Mod Mod Det Det Mod Mod the at 51 the at 35 Arg1 Arg1 Sonia Rose Bienvenue contrast but Arg1 Arg2 First Next x y x y Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 9 / 23

  26. How to represent tree-to-tree mappings? Synchronous Tree Substitution Grammars contrast but 1 A Next First g r r g A 2 be be price price Arg1 Arg2 1 A Arg0 Arg1 Arg0 Arg1 g r r g A 2 price dollar price dollar SoniaRose 51 Bienvenue 35 Mod Mod Det Det Mod Mod the at 51 the at 35 price be Arg1 Arg2 Arg0 Arg1 Arg1 Arg1 Sonia Rose Bienvenue Bienvenue 35 price dollar Mod Det Mod the at 35 Arg1 Bienvenue Howcroft (UdS) Learning Sentence Planning 24 Oct 2018 10 / 23

Recommend

CSCE 478/878 Lecture 6: Bayesian Learning MAP learners 1. Provide practical learning

CSCE 478/878 Lecture 6: Bayesian Learning MAP learners 1. Provide practical learning

Bayesian Methods Not all hypotheses are created equal (even if they are all Outline consistent with the training data) Might have reasons (domain information) to favor some Bayes Theorem hypotheses over others a priori Bayesian methods work

201 views • 6 slides
Overview Bayesian Methods for Parameter Estimation Introduction to Bayesian Statistics: Learning

Overview Bayesian Methods for Parameter Estimation Introduction to Bayesian Statistics: Learning

Overview Bayesian Methods for Parameter Estimation Introduction to Bayesian Statistics: Learning a Probability Learning the mean of a Gaussian Chris Williams Readings: Bishop 2.1 (Beta), 2.2 (Dirichlet), 2.3.6 School of Informatics,

177 views • 5 slides
Bayesian Zig Zag Developing probabilistic models using grid methods and MCMC Allen Downey ACM

Bayesian Zig Zag Developing probabilistic models using grid methods and MCMC Allen Downey ACM

Bayesian Zig Zag Developing probabilistic models using grid methods and MCMC Allen Downey ACM Learning Center Olin College February 2019 These slides tinyurl.com/zigzagacm Bayesian methods Increasingly important, but Bayesian methods

1.03k views • 92 slides
Bayesian Learning 1 Outline MLE, MAP vs. Bayesian Learning Bayesian Linear Regression

Bayesian Learning 1 Outline MLE, MAP vs. Bayesian Learning Bayesian Linear Regression

Bayesian Learning 1 Outline MLE, MAP vs. Bayesian Learning Bayesian Linear Regression Bayesian Gaussian Mixture Models Non-parametric Bayes 2 Take Away ... 1. Maximum Likelihood Estimate (MLE) = arg max p ( D| )

609 views • 27 slides
Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007 sequential decision making under uncertainty ? How Can I ... ? Move around in the physical world (e.g. driving, navigation) Play and win a game

519 views • 21 slides
Bayesian Methods for Machine Learning Radford M. Neal, University of Toronto

Bayesian Methods for Machine Learning Radford M. Neal, University of Toronto

Bayesian Methods for Machine Learning Radford M. Neal, University of Toronto http://www.cs.utoronto.ca/ radford/ NIPS Tutorial, 13 December 2004 Tutorial Outline Bayesian inference is based on using probability to represent all forms of

869 views • 67 slides
Introduc)on to Bayesian methods Lecture 14 David Sontag New

Introduc)on to Bayesian methods Lecture 14 David Sontag New

Introduc)on to Bayesian methods Lecture 14 David Sontag New York University Slides adapted from Luke Zettlemoyer, Carlos Guestrin, Dan Klein, and Vibhav Gogate Bayesian learning

497 views • 12 slides
Learning Sentence Embeddings through Tensor Methods Anima Anandkumar Joint work with Dr. Furong

Learning Sentence Embeddings through Tensor Methods Anima Anandkumar Joint work with Dr. Furong

Learning Sentence Embeddings through Tensor Methods Anima Anandkumar Joint work with Dr. Furong Huang .. ACL Workshop 2016 Representations for Text Understanding The weather is good. tree Her life spanned years of soccer incredible change

935 views • 68 slides
Learning: A Bayesian solution Dmitry P. Vetrov Research professor at HSE, Head of Bayesian

Learning: A Bayesian solution Dmitry P. Vetrov Research professor at HSE, Head of Bayesian

Open Problems in Deep Learning: A Bayesian solution Dmitry P. Vetrov Research professor at HSE, Head of Bayesian methods research group http://bayesgroup.ru Idea of the talk 2 Deep Learning Revolution in machine learning Deep neural

452 views • 26 slides
Bayesian Methods 1 Chris Williams School of Informatics, University of Edinburgh October 2015 1

Bayesian Methods 1 Chris Williams School of Informatics, University of Edinburgh October 2015 1

Bayesian Methods 1 Chris Williams School of Informatics, University of Edinburgh October 2015 1 / 23 Overview Introduction to Bayesian Statistics: Learning a Bernoulli probability Learning a discrete distribution Learning the mean

578 views • 23 slides
Hierarchical Bayesian Methods for Reinforcement Learning David Wingate wingated@mit.edu Joint

Hierarchical Bayesian Methods for Reinforcement Learning David Wingate wingated@mit.edu Joint

Hierarchical Bayesian Methods for Reinforcement Learning David Wingate wingated@mit.edu Joint work with Noah Goodman, Dan Roy, Leslie Kaelbling and Joshua Tenenbaum My Research: Agents Rich sensory data Structured prior knowledge Reasonable

1.04k views • 90 slides
Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian

Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian

Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian RL Prior knowledge, policy optimization, discussion, Bayesian approaches for other RL variants Model-free Bayesian RL Gaussian

1.23k views • 63 slides
Bayesian Learning Based on Machine Learning, T. Mitchell, McGRAW Hill, 1997, ch. 6

Bayesian Learning Based on Machine Learning, T. Mitchell, McGRAW Hill, 1997, ch. 6

0. Bayesian Learning Based on Machine Learning, T. Mitchell, McGRAW Hill, 1997, ch. 6 Acknowledgement: The present slides are an adaptation of slides drawn by T. Mitchell 1. Two Roles for the Bayesian Methods in Learning 1. Provides

709 views • 54 slides
Bayesian Learning Based on Machine Learning, T. Mitchell, McGRAW Hill, 1997, ch. 6

Bayesian Learning Based on Machine Learning, T. Mitchell, McGRAW Hill, 1997, ch. 6

0. Bayesian Learning Based on Machine Learning, T. Mitchell, McGRAW Hill, 1997, ch. 6 Acknowledgement: The present slides are an adaptation of slides drawn by T. Mitchell 1. Two Roles for the Bayesian Methods in Learning 1. Provides

1.15k views • 71 slides
Bayesian networks Andrea Passerini passerini@disi.unitn.it Machine Learning Bayesian networks

Bayesian networks Andrea Passerini passerini@disi.unitn.it Machine Learning Bayesian networks

Bayesian networks Andrea Passerini passerini@disi.unitn.it Machine Learning Bayesian networks Graphical models Why All probabilistic inference and learning amount at repeated applications of the sum and product rules Probabilistic graphical

361 views • 34 slides
Bayesian networks Andrea Passerini passerini@disi.unitn.it Machine Learning Bayesian networks

Bayesian networks Andrea Passerini passerini@disi.unitn.it Machine Learning Bayesian networks

Bayesian networks Andrea Passerini passerini@disi.unitn.it Machine Learning Bayesian networks Graphical models Why All probabilistic inference and learning amount at repeated applications of the sum and product rules Probabilistic graphical

797 views • 33 slides
Bayesian Methods in Cryo-EM Marcus A. Brubaker York University / Structura Biotechnology Toronto,

Bayesian Methods in Cryo-EM Marcus A. Brubaker York University / Structura Biotechnology Toronto,

Bayesian Methods in Cryo-EM Marcus A. Brubaker York University / Structura Biotechnology Toronto, Canada Bayesian Methods in Cryo-EM Bayesian methods already underpin many successful techniques Likelihood methods for refinement/3D classification

600 views • 29 slides
Stochastic particle methods in Bayesian statistical learning P. Del Moral (INRIA team ALEA) INRIA

Stochastic particle methods in Bayesian statistical learning P. Del Moral (INRIA team ALEA) INRIA

Stochastic particle methods in Bayesian statistical learning P. Del Moral (INRIA team ALEA) INRIA & Bordeaux Mathematical Institute & X CMAP INRIA Workshop on Statistical Learning IHP Paris, Dec. 5-6, 2011 Some hyper-refs

820 views • 69 slides
CS440/ECE448 Lecture 15: Bayesian Inference and Bayesian Learning Slides by Svetlana Lazebnik,

CS440/ECE448 Lecture 15: Bayesian Inference and Bayesian Learning Slides by Svetlana Lazebnik,

CS440/ECE448 Lecture 15: Bayesian Inference and Bayesian Learning Slides by Svetlana Lazebnik, 10/2016 Modified by Mark Hasegawa-Johnson, 3/2019 Bayesian Inference and Bayesian Learning Bayes Rule Bayesian Inference Misdiagnosis

829 views • 38 slides
CSCE 478/878 Lecture 7: Bayesian Learning Stephen D. Scott (Adapted from Tom Mitchells slides)

CSCE 478/878 Lecture 7: Bayesian Learning Stephen D. Scott (Adapted from Tom Mitchells slides)

CSCE 478/878 Lecture 7: Bayesian Learning Stephen D. Scott (Adapted from Tom Mitchells slides) October 31, 2006 1 Bayesian Methods Not all hypotheses are created equal (even if they are all consistent with the training data) Might have

507 views • 34 slides
Learning Objectives At the end of the class you should be able to: derive Bayesian learning from

Learning Objectives At the end of the class you should be able to: derive Bayesian learning from

Learning Objectives At the end of the class you should be able to: derive Bayesian learning from first principles explain how the Beta and Dirichlet distributions are used for Bayesian learning. D. Poole and A. Mackworth 2019 c Artificial

272 views • 16 slides
Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness Ian Goodfellow, OpenAI Research Scientist NIPS 2016 Workshop on Bayesian Deep Learning Barcelona, 2016-12-10 Speculation on Three Topics Can we

769 views • 21 slides
Bayesian Methods in Reinforcement Learning Wednesday, June 20th, 2007 ICML-07 tutorial

Bayesian Methods in Reinforcement Learning Wednesday, June 20th, 2007 ICML-07 tutorial

Bayesian Methods in Reinforcement Learning Wednesday, June 20th, 2007 ICML-07 tutorial Corvallis, Oregon, USA Pascal Poupart (Univ. of Waterloo) Mohammad Ghavamzadeh (Univ. of Alberta) Yaakov Engel (Univ. of Alberta) Motivation Why a

892 views • 67 slides
Why Bayesian methods in Simulation? Simulation Simulation Model Inputs BAYESIAN IDEAS

Why Bayesian methods in Simulation? Simulation Simulation Model Inputs BAYESIAN IDEAS

Outline Why Bayesian methods in Simulation? Simulation Simulation Model Inputs BAYESIAN IDEAS Output Random Simulated Statistical, pr FOR DISCRETE EVENT SIMULATION: Y r Numbers Variates Control,

473 views • 20 slides

More recommend