Dialog as a Vehicle for Lifelong Learning Aishwarya Padmakumar, - - PowerPoint PPT Presentation

dialog as a vehicle for lifelong learning
SMART_READER_LITE
LIVE PREVIEW

Dialog as a Vehicle for Lifelong Learning Aishwarya Padmakumar, - - PowerPoint PPT Presentation

Dialog as a Vehicle for Lifelong Learning Aishwarya Padmakumar, Raymond J. Mooney Department of Computer Science The University of Texas at Austin Standard Supervised Learning Pipeline Collect Train Test Labelled Model Model Data


slide-1
SLIDE 1

Dialog as a Vehicle for Lifelong Learning

Aishwarya Padmakumar, Raymond J. Mooney

Department of Computer Science The University of Texas at Austin

slide-2
SLIDE 2

Standard Supervised Learning Pipeline

Collect Labelled Data Test Model Train Model

slide-3
SLIDE 3

Standard Machine Learning Pipeline - Disadvantages

  • Real world test data may look different

from training data.

  • Test distribution may change over time.
  • Tasks needed by users may change over

time.

  • Needs dedicated dataset for each task.
slide-4
SLIDE 4

Lifelong Learning

Initial Task(s), Data Test Model Train Model Additional Task(s), Data

slide-5
SLIDE 5

Lifelong Learning - Benefits

  • Generalizable - adapt to a variety of test

data distributions

  • Versatile - same model can be shared

between multiple tasks, that are not necessarily pre-defined

slide-6
SLIDE 6

Lifelong Learning - Benefits

slide-7
SLIDE 7

Challenge Area

  • Dialog for Supporting Lifelong Learning -

New challenge area for dialog researchers

  • Dialog systems interact with users by

design - Provide a mechanism to collect labeled data at test time.

slide-8
SLIDE 8

Active Learning

8

?

Query for labels most likely to improve the model.

slide-9
SLIDE 9

Opportunistic Active Learning

9

  • Asking locally convenient questions during an

interactive task.

  • Questions may not be useful for the current

interaction but expected to help future tasks.

slide-10
SLIDE 10

Opportunistic Active Learning

Bring the blue mug from Alice’s office Would you use the word “blue” to refer to this object? Yes

10

slide-11
SLIDE 11

Opportunistic Active Learning

Bring the blue mug from Alice’s office Would you use the word “tall” to refer to this object? Yes

11

slide-12
SLIDE 12

Challenge Problems for Dialog Researchers

slide-13
SLIDE 13

Challenge: Dialog Act Design

Design new dialog acts that collect labeled data or combine this with task-completion objectives Can you show me how to

  • pen this with

a knife?

slide-14
SLIDE 14

Challenge: Dataset Collection and Simulation

Collect annotations to provide correct answers in simulation to a wide range of queries.

slide-15
SLIDE 15

Challenge: Prosodic Analysis

  • Identify urgency, stress, sarcasm and

frustration in users to determine when it is appropriate to include or avoid data collection queries.

  • User studies to identify best practices for

demonstrating learning.

slide-16
SLIDE 16

Dialog as a Vehicle for Lifelong Learning

Aishwarya Padmakumar, Raymond J. Mooney

Department of Computer Science The University of Texas at Austin

slide-17
SLIDE 17

Thank You!

Contact: aish@cs.utexas.edu