predicting implicit and explicit questions
play

Predicting implicit and explicit questions Matthijs Westera COLT - PowerPoint PPT Presentation

Jan 15, 2024 •196 likes •801 views

Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop = Computational Linguistics & Linguistic Theory The data of

  1. Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop

  2. Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop = Computational Linguistics & Linguistic Theory

  3. The data of linguistic theory:

  4. The data of linguistic theory: g m a t i c s ) n t i c s & P r a ( S e m a

  5. The data of linguistic theory: g m a t i c s ) n t i c s & P r a ( S e m a

  6. The data of computational ling:

  7. The data of computational ling:

  8. Main interest messy crisp

  9. Main interest messy crisp enables

  10. Main interest messy crisp enables How?

  11. Main interest messy crisp enables How? - ... ? - ... ? - ... ?

  12. Neural networks

  13. Neural networks crisp

  14. Neural networks messy crisp

  15. Neural networks messy crisp ? ?

  16. Neural networks messy crisp ? ? cf. Aina et al. (2018) [SemEval]

  17. Distributional & formal semantics

  18. Distributional & formal semantics cat animal red

  19. Distributional & formal semantics messy cat animal red

  20. Distributional & formal semantics messy ∃ x (R ED ( x ) ∧ C AT ( x )) cat animal red

  21. Distributional & formal semantics messy crisp ∃ x (R ED ( x ) ∧ C AT ( x )) cat animal red

  22. Distributional & formal semantics messy crisp ∃ x (R ED ( x ) ∧ C AT ( x )) cat animal ? ? red

  23. Distributional & formal semantics messy crisp ∃ x (R ED ( x ) ∧ C AT ( x )) cat animal ? ? red Westera & Boleda (under review)

  24. Main interest messy crisp enables How?

  25. Main interest messy crisp enables How? - how do NN models do it?

  26. Main interest messy crisp enables How? - how do NN models do it? - how do DS and FS relate?

  27. Main interest messy crisp enables How? - how do NN models do it? - how do DS and FS relate? - what does ling. theory say?

  28. Main interest messy crisp enables How? - how do NN models do it? - how do DS and FS relate? - what does ling. theory say?

  29. Pragmatics

  30. Pragmatics € PAINT

  31. Pragmatics € PAINT

  32. Pragmatics

  33. Pragmatics

  34. Pragmatics

  35. Main interest messy crisp enables How? - how do NN models do it? - how do DS and FS relate? - what does ling. theory say?

  36. Main interest messy crisp enables How? - how do NN models do it? - how do DS and FS relate? - ...

  37. Main interest messy crisp enables How? - how do NN models do it? - how do DS and FS relate? - how are goals identifjed?

  38. Main interest messy crisp enables How? - how do NN models do it? - how do DS and FS relate? - how are goals identifjed?

  39. Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop

  40. Discourse goals Pragmatic theory:

  41. Discourse goals Pragmatic theory: ● Discourse is organized around questions:

  42. Discourse goals Pragmatic theory: e.g., Westera 2017 (PhD thesis) ● Discourse is organized around questions:

  43. Discourse goals Pragmatic theory: e.g., Westera 2017 (PhD thesis) ● Discourse is organized around questions: – Some explicit (“What color do you want?”) – Most are implicit:

  44. Discourse goals Pragmatic theory: e.g., Westera 2017 (PhD thesis) ● Discourse is organized around questions: – Some explicit (“What color do you want?”) – Most are implicit: So, there's this party tonight... August, no! But it's perfect! It’s my last night in Aberdeen! I'll never be in this town again! No, we can't. BookCorpus/590124__come-as-you-are.txt

  45. Discourse goals Pragmatic theory: e.g., Westera 2017 (PhD thesis) ● Discourse is organized around questions: – Some explicit (“What color do you want?”) – Most are implicit: ? ? o g So, there's this party tonight... e w August, no! l l a h But it's perfect! It’s my last night in Aberdeen! I'll never be in this S town again! No, we can't. BookCorpus/590124__come-as-you-are.txt

  46. Discourse goals Pragmatic theory: e.g., Westera 2017 (PhD thesis) ● Discourse is organized around questions: – Some explicit (“What color do you want?”) – Most are implicit: ? ? o g So, there's this party tonight... e w August, no! l l a h But it's perfect! It’s my last night in Aberdeen! I'll never be in this S town again! No, we can't. BookCorpus/590124__come-as-you-are.txt

  47. Question prediction Get a model to predict implicit questions (goals), by training on explicit questions.

  48. Question prediction Get a model to predict implicit questions (goals), by training on explicit questions. = f v i s i o n ! r e e s u p e r

  49. Question prediction Get a model to predict implicit questions (goals), by training on explicit questions. = f v i s i o n ! r e e s u p e r Data: Only dialogue contains enough questions. ●

  50. Question prediction Get a model to predict implicit questions (goals), by training on explicit questions. = f v i s i o n ! r e e s u p e r Data: Only dialogue contains enough questions. ● Extract dialogues from movie scripts and books. ● – E.g., 1M dialogues from BookCorpus.

  51. Question prediction Get a model to predict implicit questions (goals), by training on explicit questions. = f v i s i o n ! r e e s u p e r Data: Only dialogue contains enough questions. ● Extract dialogues from movie scripts and books. ● – E.g., 1M dialogues from BookCorpus. Models (e.g.): Simple word-level RNN. (Westera 2018 [SemDial]) ●

  52. Question prediction Get a model to predict implicit questions (goals), by training on explicit questions. = f v i s i o n ! r e e s u p e r Data: Only dialogue contains enough questions. ● Extract dialogues from movie scripts and books. ● – E.g., 1M dialogues from BookCorpus. Models (e.g.): Simple word-level RNN. (Westera 2018 [SemDial]) ● Sentence-level RNN on pre-trained sent. embeddings. ●

  53. Example (aim) So, there's this party tonight… So, there's this party tonight… August, no! August, no! But it's perfect! It’s my last night in Aberdeen! I'll never be in this But it's perfect! It’s my last night in Aberdeen! I'll never be in this town again! town again! BookCorpus/590124__come-as-you-are.txt No, we can't. No, we can't.

  54. Example (aim) So, there's this party tonight… So, there's this party tonight… Shall we go? Shall we go? August, no! August, no! But it's perfect! It’s my last night in Aberdeen! I'll never be in this But it's perfect! It’s my last night in Aberdeen! I'll never be in this town again! town again! BookCorpus/590124__come-as-you-are.txt No, we can't. No, we can't.

  55. Example (aim) So, there's this party tonight… So, there's this party tonight… Shall we go? Shall we go? August, no! August, no! Why do you even bring it up? Why do you even bring it up? But it's perfect! It’s my last night in Aberdeen! I'll never be in this But it's perfect! It’s my last night in Aberdeen! I'll never be in this town again! town again! BookCorpus/590124__come-as-you-are.txt No, we can't. No, we can't.

  56. Example (aim) So, there's this party tonight… So, there's this party tonight… Shall we go? Shall we go? August, no! August, no! Why do you even bring it up? Why do you even bring it up? But it's perfect! It’s my last night in Aberdeen! I'll never be in this But it's perfect! It’s my last night in Aberdeen! I'll never be in this town again! town again! BookCorpus/590124__come-as-you-are.txt Can we go? Can we go? No, we can't. No, we can't.

  57. Example (aim) So, there's this party tonight… So, there's this party tonight… Shall we go? Shall we go? August, no! August, no! Why do you even bring it up? Why do you even bring it up? But it's perfect! It’s my last night in Aberdeen! I'll never be in this But it's perfect! It’s my last night in Aberdeen! I'll never be in this town again! town again! BookCorpus/590124__come-as-you-are.txt Can we go? Can we go? No, we can't. No, we can't. Why can’t we go? Why can’t we go?

  58. Summary messy crisp enables - how do NN models do it? How? - how do DS and FS relate? - can we predict discourse goals?

  59. Predicting implicit and explicit questions Matthijs Westera COLT kick-off workshop

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

Not Smooth High degree approximation Explicit y=f(x) Implicit f(x,y)=0 Parametric

Not Smooth High degree approximation Explicit y=f(x) Implicit f(x,y)=0 Parametric

Polylines: Piecewise linear approximation to curves Not Smooth High degree approximation Explicit y=f(x) Implicit f(x,y)=0 Parametric x=x(t), y=y(t) Explicit Representation y = f ( x ) Essentially a function plot over some

582 views • 29 slides
Session 14: Explicit and Implicit Cooperation 1. Nash equilibrium versus collective action.

Session 14: Explicit and Implicit Cooperation 1. Nash equilibrium versus collective action.

Session 14: Explicit and Implicit Cooperation 1. Nash equilibrium versus collective action. 2. Honeywell-GE merger. 3. P&M meets LPG: Sustaining cooperation through repeated interaction. Session 14 Explicit and Implicit Cooperation

492 views • 14 slides
Implicit Graphs Implicit Graph: Only a subset, possibly only one, of the vertices is

Implicit Graphs Implicit Graph: Only a subset, possibly only one, of the vertices is

2/23/2016 Explicit vs Implicit Graphs Explicit Graph: All vertices are identified individually and represented separately. CSE373: Data Structures and Algorithms All edges are identified individually and represented separately.

69 views • 4 slides
2.1 Explicit & Implicit Surfaces Hao Li http://cs599.hao-li.com 1 Administrative

2.1 Explicit & Implicit Surfaces Hao Li http://cs599.hao-li.com 1 Administrative

Spring 2015 CSCI 599: Digital Geometry Processing 2.1 Explicit & Implicit Surfaces Hao Li http://cs599.hao-li.com 1 Administrative Exercise 1 discussion: Next Tuesday Hao Li (Instructor) Office Hour: Tue 2:00 PM - 4:00

848 views • 68 slides
2.1 Explicit & Implicit Surfaces Hao Li http://cs621.hao-li.com 1 Administrative

2.1 Explicit & Implicit Surfaces Hao Li http://cs621.hao-li.com 1 Administrative

Spring 2019 CSCI 621: Digital Geometry Processing 2.1 Explicit & Implicit Surfaces Hao Li http://cs621.hao-li.com 1 Administrative Exercise 1 discussion: Next Time! Hao Li (Instructor) Office Hour: Tue 12:30 PM - 1:30 PM, SAL

818 views • 68 slides
Combining Implicit and Explicit Topic Representations for Result Diversification Jiyin He, Vera

Combining Implicit and Explicit Topic Representations for Result Diversification Jiyin He, Vera

Combining Implicit and Explicit Topic Representations for Result Diversification Jiyin He, Vera Hollink, Arjen de Vries Centrum Wiskunde & Informatica SIGIR 2012, Portland 1 Subtopics in result diversification Python 2 Implicit

600 views • 18 slides
Explicit vs Implicit CommunicaGon in Control Anant Sahai UC

Explicit vs Implicit CommunicaGon in Control Anant Sahai UC

Explicit vs Implicit CommunicaGon in Control Anant Sahai UC Berkeley Joint with Se Yong Park and Pulkit Grover Thanks to NSF for funding this

1.03k views • 46 slides
Higher prices Hotels set prices Higher prices help others Low speeds Driving Higher speeds

Higher prices Hotels set prices Higher prices help others Low speeds Driving Higher speeds

P1 SepOct 2012 Timothy Van Zandt Prices & Markets Page 1 Session 14 Explicit and Implicit Cooperation Session 14: Explicit and Implicit Cooperation 1 1. Nash equilibrium versus collective action. 2. Honeywell-GE

293 views • 7 slides
A COMPARISON OF IMPLICIT AND EXPLICIT FINITE ELEMENT METHODS FOR THE MESO-LEVEL SIMULATION OF DRY

A COMPARISON OF IMPLICIT AND EXPLICIT FINITE ELEMENT METHODS FOR THE MESO-LEVEL SIMULATION OF DRY

18 TH INTERNATIONAL CONFERENCE ON COMPOSITE MATERIALS A COMPARISON OF IMPLICIT AND EXPLICIT FINITE ELEMENT METHODS FOR THE MESO-LEVEL SIMULATION OF DRY WOVEN FABRIC COMPOSITES M. Komeili, A. S. Milani School of Engineering, University of British

326 views • 6 slides
HYPERBOLIC EXPLICIT-PARABOLIC LINEARLY IMPLICIT FINITE DIFFERENCE METHODS FOR DEGENERATE

HYPERBOLIC EXPLICIT-PARABOLIC LINEARLY IMPLICIT FINITE DIFFERENCE METHODS FOR DEGENERATE

Fourteenth International Conference on Hyperbolic Problems: Theory, Numerics and Applications HYP2012 HYPERBOLIC EXPLICIT-PARABOLIC LINEARLY IMPLICIT FINITE DIFFERENCE METHODS FOR DEGENERATE CONVECTION DIFFUSION EQUATIONS F . Cavalli

524 views • 51 slides
Second order Implicit-Explicit Total Variation Diminishing schemes for the Euler system in the

Second order Implicit-Explicit Total Variation Diminishing schemes for the Euler system in the

Second order Implicit-Explicit Total Variation Diminishing schemes for the Euler system in the low Mach regime Victor Michel-Dansac Sminaire ANEDP , Lille, 22/03/2018 Giacomo Dimarco, Univ. of Ferrara, Italy Raphal Loubre, Univ. of

661 views • 40 slides
Second order Implicit-Explicit Total Variation Diminishing schemes for the Euler system in the

Second order Implicit-Explicit Total Variation Diminishing schemes for the Euler system in the

Second order Implicit-Explicit Total Variation Diminishing schemes for the Euler system in the low Mach regime Victor Michel-Dansac Workshop NumWave, 13 December 2017 Giacomo Dimarco, Univ. of Ferrara, Italy Raphal Loubre, Univ. of

465 views • 32 slides
Implicit-Explicit Runge-Kutta schemes for the Boltzmann-Poisson equation for semiconductors

Implicit-Explicit Runge-Kutta schemes for the Boltzmann-Poisson equation for semiconductors

Implicit-Explicit Runge-Kutta schemes for the Boltzmann-Poisson equation for semiconductors Vittorio Rispoli In collaboration with: G. Dimarco (Univ. of Toulouse, France) L. Pareschi (Univ. of Ferrara, Italy) HYP2012 University of Padova

498 views • 34 slides
GCMs with Implicit and Explicit Representation of Cloud Microphysics: Simulation of Extreme

GCMs with Implicit and Explicit Representation of Cloud Microphysics: Simulation of Extreme

GCMs with Implicit and Explicit Representation of Cloud Microphysics: Simulation of Extreme Precipitation In-Sik Kang Seoul National University Yang, Young-Min (2014, Ph.D. thesis); Ahn, Min-Seop (2017, Ph.D. thesis) Kang et al. (2015, Climate

741 views • 52 slides
From Explicit to Implicit Dynamic Frames in Java Dynamic Logic and KeY . Wojciech Mostowski

From Explicit to Implicit Dynamic Frames in Java Dynamic Logic and KeY . Wojciech Mostowski

. . . From Explicit to Implicit Dynamic Frames in Java Dynamic Logic and KeY . Wojciech Mostowski Halmstad University . . NWPT 2015, 21 st October 2015 hh.se . . Overview 1 Context 2 Permission-based verification 3 Permissions with

755 views • 43 slides
Implicit and Explicit Risk Perception, Affect, and Trust: An Investigation of Food Traffic

Implicit and Explicit Risk Perception, Affect, and Trust: An Investigation of Food Traffic

Implicit and Explicit Risk Perception, Affect, and Trust: An Investigation of Food Traffic Lights. Tony McCarthy, Calvin Burns, & Matthew Revie. Risk, Perception, and Response Conference. Harvard Center for Risk Analysis. 20th-21st

312 views • 16 slides
IMplicit-EXplicit schemes for BGK kinetic equations Sandra Pieraccini, Gabriella Puppo

IMplicit-EXplicit schemes for BGK kinetic equations Sandra Pieraccini, Gabriella Puppo

IMplicit-EXplicit schemes for BGK kinetic equations Sandra Pieraccini, Gabriella Puppo Politecnico di Torino Dipartimento di Matematica HYP06, Lyon, July 17-21 p.1/22 Boltzmann equation Rarefied gas flow obeys Boltzmann equation which

745 views • 45 slides
Object Detection Sanja Fidler CSC420: Intro to Image Understanding 1 / 48 Object Detection The

Object Detection Sanja Fidler CSC420: Intro to Image Understanding 1 / 48 Object Detection The

Object Detection Sanja Fidler CSC420: Intro to Image Understanding 1 / 48 Object Detection The goal of object detection is to localize objects in an image and tell their class Localization: place a tight bounding box around object Most

1.17k views • 91 slides
Numerical Methods for LargeScale Eigenvalue Problems Patrick K urschner Max Planck

Numerical Methods for LargeScale Eigenvalue Problems Patrick K urschner Max Planck

Summer School in Trogir, Croatia Oktober 12, 2011 Numerical Methods for LargeScale Eigenvalue Problems Patrick K urschner Max Planck Institute for Dynamics of Complex Technical Systems Computational Methods in Systems and Control Theory

298 views • 17 slides
' $ r r r r INSTITUT F UR INF ORMA TIK r r r r r r r r r r r r r

' $ r r r r INSTITUT F UR INF ORMA TIK r r r r r r r r r r r r r

' $ r r r r INSTITUT F UR INF ORMA TIK r r r r r r r r r r r r r Ulrich R ude r r r ' $ Multilevel Eigenvalue Solvers fo r the Multigroup Diusion Equations U. R ude and W. Schmid T

862 views • 13 slides
Links visited in class implied volatility of asset from call option value artificial data plot

Links visited in class implied volatility of asset from call option value artificial data plot

14.0 Implied volatility Links visited in class implied volatility of asset from call option value artificial data plot Newton iter- ates.html 1

612 views • 6 slides
Optimal Portfolio under Fractional Stochastic Environment Ruimeng Hu Joint work with Jean-Pierre

Optimal Portfolio under Fractional Stochastic Environment Ruimeng Hu Joint work with Jean-Pierre

Introduction Fractional Stochastic Volatility under Power Utility General Utility Optimal Portfolio under Fractional Stochastic Environment Ruimeng Hu Joint work with Jean-Pierre Fouque Department of Statistics and Applied Probability

445 views • 33 slides
Asymptotics for local volatility and Sabr models Peter Laurence Facolt di Statistica,

Asymptotics for local volatility and Sabr models Peter Laurence Facolt di Statistica,

Collaborators in various aspects of work presented today Outline of Work to be discussed Background Our Approach and Results Asymptotics for local volatility and Sabr models Peter Laurence Facolt di Statistica, Universit di Roma I

831 views • 65 slides
Housing and Neighbourhood Service Customer Service Away Day June 2019 1 What is today for?

Housing and Neighbourhood Service Customer Service Away Day June 2019 1 What is today for?

Housing and Neighbourhood Service Customer Service Away Day June 2019 1 What is today for? Today is about taking some time out to: 1. Find out about whats going on in the Service 2. Take part in group work on Customer Service 2

509 views • 17 slides

More recommend