Outline 1 Motivation 2 Method 3 Models 4 Results 5 Criticism Murphy, - - PowerPoint PPT Presentation

▶

May 31, 2023 346 likes •409 views

Motivation Method Models Results Criticism Outline 1 Motivation 2 Method 3 Models 4 Results 5 Criticism Murphy, B.; Baroni, M.; Poesio, M. : EEG responds to conceptual stimuli and corpus semantics Course: Mechanisms of meaning Institute for

SLIDE 1

Motivation Method Models Results Criticism

Outline

1 Motivation 2 Method 3 Models 4 Results 5 Criticism

Murphy, B.; Baroni, M.; Poesio, M.: EEG responds to conceptual stimuli and corpus semantics

Course: Mechanisms of meaning Institute for Logic, Language and Computation Paper: EEG responds to conceptual stimuli and corpus semantics

SLIDE 2

Motivation Method Models Results Criticism

Motivation

Brain imaging in linguistics Might help isolating semantic aspects from others fMRI (functional magnetic resonance imaging) measures blood flow in brain regions high spatial resolution (millimeters) low temporal resolution (seconds) high costs EEG (electroencephalography) measures electric currents on the scalp low spacial resolution (centimeters) high temporal resolution (milliseconds) moderate costs

Course: Mechanisms of meaning Institute for Logic, Language and Computation Paper: EEG responds to conceptual stimuli and corpus semantics

SLIDE 3

Motivation Method Models Results Criticism

Method

Subjects are confronted with pictures of

animals tools

Task is to name them Brain activity is recorded Corpus models are trained with most of the data Models are used to predict for remaining data

whether an animal or a tool was viewed (between categories) which animal or tool was viewed (within categories)

Course: Mechanisms of meaning Institute for Logic, Language and Computation Paper: EEG responds to conceptual stimuli and corpus semantics

SLIDE 4

Motivation Method Models Results Criticism

Models

Search engine (Yahoo!)

nly allows for searching co-occurrence

huge Newspaper (la repubblica) different feature sets

window co-occurrence in sentences position discriminates position of verb wrt noun dependency filter filters by paths dependency path paths as features

comparatively small

Course: Mechanisms of meaning Institute for Logic, Language and Computation Paper: EEG responds to conceptual stimuli and corpus semantics

SLIDE 5

Motivation Method Models Results Criticism

Results

The Yahoo! and the window model render results over chance The worse performance of the more sophisticated corpus models is attributed to their sparseness Between categories predictions were more accurate than within categories

involved concepts are more similar all concepts were learned with the same feature sets

Course: Mechanisms of meaning Institute for Logic, Language and Computation Paper: EEG responds to conceptual stimuli and corpus semantics

SLIDE 6

Motivation Method Models Results Criticism

Criticism

Not convinced how this rules out non-linguistic associations Shouldn’t those patterns be cross subject? Training 58 data sets and predicting 2 seems to be a clear case of overfitting

Course: Mechanisms of meaning Institute for Logic, Language and Computation Paper: EEG responds to conceptual stimuli and corpus semantics