Neural representation of linguistic feature Neural representation of - PowerPoint PPT Presentation

Aug 27, 2022 •161 likes •294 views

Neural representation of linguistic feature Neural representation of linguistic feature hierarchy reflects language proficiency hierarchy reflects language proficiency Giovanni Di Liberto Jinping Nie Jeremy Yeaton, Bahar Khalighinejad, Shihab

Neural representation of linguistic feature Neural representation of linguistic feature hierarchy reflects language proficiency hierarchy reflects language proficiency Giovanni Di Liberto Jinping Nie Jeremy Yeaton, Bahar Khalighinejad, Shihab Shamma, *Nima Mesgarani
Speech processing hierarchy • Learning a new language requires learning new sounds ( phonemes ), new sound combinations ( phonotactics ), and new words ( semantic ) • Language acquisition is cumulative; proficiency can be quantified (e.g., Basic, Independent, Proficient) • How does language proficiency change the neural representation of linguistic feature hierarchy?
Native (L1) and non-native (L2) English speaking subjects Language proficiency: Number of subjects: 17 16 16 22 71 total • L1: 22 Native English speakers • L2: 49 Native Mandarin speaker with instructed English acquisition • No significant difference between age and time in the US
Experimental procedure 1.5 hours continuous speech stories, divided into 24 blocks, alternating male and female speakers (4 speakers total) Similar task engagement
600 ms Regression weights (a.k.a TRF) show the contribution of each feature to the response Lalor ‘ 2009, Di Liberto ‘ 2016,2019, Broderick ‘ 2018, Brodbeck ‘ 2018
Hypotheses With increased language proficiency in L2 subjects, the neural representation of: 1. Low-level acoustic attributes will not change 2. English phonemes will be more similar to L1 (learned phonetics ) 3. Phonotactics will approach L1, but not entirely to preserve L2 phonotactics (learned phonotactics ) 4. Semantic dissimilarity becomes more pronounced (learned words )
Envelope TRF • Reflects the processing of basic acoustic features • No significant change with proficiency
Phoneme TRF Proficiency shifts the neural representation of phonemes toward L1
Increased phoneme similarity to L1 is higher for English-only phonemic contrasts
Learning new phoneme sequences: phonotactic TRFs • Early negative in all L2 subjects, but not in L1 (~240 ms) • Late Negative for L1 & C (~360ms), and even later for A & B (~ 480 ms)
Semantic dissimilarity TRF • Early negative in L1 subjects (~240 ms), Later in C (~360 ms) • Weaker in A & B
Predicting language proficiency from TRFs Language proficiency is highly predictable from EEG High classification accuracy for L1 vs. L2 , but also L1 vs. C
Proficiency changes the encoding of linguistic hierarchy in EEG responses to continous speech phonemes phonotactics semantic • Objective measure of proficiency & nativeness • Age of acquisition, frequency of exposure, etc.

Recommend

Neural Information Retrieval Wassila Lalouani 1 Plan Neural network architectures Neural

Neural Information Retrieval Wassila Lalouani 1 Plan Neural network architectures Neural IR tasks Neural IR architecture Feature Representations Neural IR query auto completion Neural IR query suggestion Neural IR document

1.48k views • 18 slides

Neural Network Approaches to Representation Learning for NLP Navid Rekabsaz Idiap Research

Neural Network Approaches to Representation Learning for NLP Navid Rekabsaz Idiap Research Institute @navidrekabsaz navid.rekabsaz@idiap.ch Agenda Brief Intro to Deep Learning - Neural Networks Word Representation Learning - Neural

774 views • 40 slides

Neural Discrete Representation Learning (VQ-VAE) Aaron van den Oord, Oriol Vinyals, Koray

Neural Discrete Representation Learning (VQ-VAE) Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu Google Deepmind NIPS 2017 Neural Discrete Representation Learning 1. What is the task? 2. Comparison & Contribution 3. VQ-VAE Model

391 views • 23 slides

Local Representation Alignment: A Biologically Motivated Algorithm for Training Neural Systems

Local Representation Alignment: A Biologically Motivated Algorithm for Training Neural Systems Alexander G. Ororbia II The Neural Adaptive Computing (NAC) Laboratory Rochester Institute of Technology 1 Collaborators The Pennsylvania State

849 views • 65 slides

8 Neural MT 2: Attentional Neural MT In the past chapter, we described a simple model for neural

8 Neural MT 2: Attentional Neural MT In the past chapter, we described a simple model for neural machine translation, which uses an encoder to encode sentences as a fixed-length vector. However, in some ways, this view is overly simplified, and

635 views • 9 slides

Detection and Localisation of Neural Responses to Linguistic Phenomena using Machine Learning

Detection and Localisation of Neural Responses to Linguistic Phenomena using Machine Learning Student: Mehdi Parviz Supervisor: Mark Johnson Department of Computing Macquarie University COMP901, 2012 1 / 23 Outline Introduction Background

382 views • 23 slides

Representing symbolic linguistic structures for neural NLP: methods and applications Alexander

Representing symbolic linguistic structures for neural NLP: methods and applications Alexander Panchenko Assistant Professor for NLP Structure and goals of this talk Publishing in ACL and similar conferences, e.g. NAACL, EMNLP , CoNLL:

999 views • 51 slides

Representing symbolic linguistic structures for neural NLP: methods and applications Alexander

Representing symbolic linguistic structures for neural NLP: methods and applications Alexander Panchenko Assistant Professor for NLP About myself: a decade of fun R&D in NLP 2002-2008: Bauman Moscow State Technical University ,

883 views • 45 slides

IN5550 Neural Methods in Natural Language Processing Convolutional Neural Networks Erik

IN5550 Neural Methods in Natural Language Processing Convolutional Neural Networks Erik Velldal University of Oslo 25 February 2020 So far: MLPs + embeddings as inputs Embeddings have benefits over discrete feature vectors; makes

902 views • 35 slides

IN5550 Neural Methods in Natural Language Processing Convolutional Neural Networks Erik

806 views • 58 slides

Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Learning in Neural Networks w 1,3 w 3,5 1 3 5 w w 1,4 3,6 w w 2,3 4,5 2 4 6 w w 2,4 4,6 Class #18: Back-Propagation; } A neural network can learn a classification function by Tuning Hyper-Parameters adjusting its weights to

259 views • 4 slides

Posterior odds interpretation of a sigmoid Artificial Intelligence: Neural Networks Michael S.

Artificial Intelligence: Representation and Problem Solving 15-381 January 16, 2007 Neural Networks Topics decision boundaries linear discriminants perceptron gradient learning neural networks Artificial Intelligence:

539 views • 19 slides

Transition-based Parsing with Neural Nets Graham Neubig Site

CS11-747 Neural Networks for NLP Transition-based Parsing with Neural Nets Graham Neubig Site https://phontron.com/class/nn4nlp2017/ Two Types of Linguistic Structure Dependency: focus on relations between words ROOT I saw a girl

641 views • 38 slides

Improving neural networks by preventing co- adaption of feature detectors Published by: G.E.

Improving neural networks by preventing co- adaption of feature detectors Published by: G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever and R. R. Salakhutdinov Presented by: Melvin Laux TEst | adhssahSS2013 Text Analytics | Computer

502 views • 27 slides

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views • 17 slides

Natural Image Statistics and Neural Representation Eero P Simoncelli Bruno A Olshusen Center for

Natural Image Statistics and Neural Representation Eero P Simoncelli Bruno A Olshusen Center for Neural Science Center for Neuroscience New York University University of California, Davis Presenter Shilin Zhu Visual Computing Center University

599 views • 25 slides

SuperGlue: Learning Feature Matching with Graph Neural Networks Paul-Edouard Sarlin 1 Daniel

SuperGlue: Learning Feature Matching with Graph Neural Networks Paul-Edouard Sarlin 1 Daniel DeTone 2 Tomasz Malisiewicz 2 Andrew Rabinovich 2 Feature matching is ubiquitous 3D reconstruction Visual localization SLAM Place

256 views • 25 slides

Neural LMs Image: (Bengio et al, 03) One Hot Vectors Neural LMs (Bengio et al, 03)

Neural LMs Image: (Bengio et al, 03) One Hot Vectors Neural LMs (Bengio et al, 03) Low-dimensional Representations Learning representations by back-propagating errors Rumelhart, Hinton & Williams, 1986 A neural

1.64k views • 114 slides

Neural networks regularization through representation learning - presentation of my PhD work -

Neural networks regularization through representation learning - presentation of my PhD work - Japanese-French workshop on optimization for machine learning (Riken & LITIS), INSA de Rouen. Sept.25 th , 2017 Soufiane Belharbi Romain Hrault

1.02k views • 76 slides

Neural Classification of Linguistic Coherence using Long Short-Term Memories Pashutan Modaresi,

Neural Classification of Linguistic Coherence using Long Short-Term Memories Pashutan Modaresi, Matthias Liebeck and Stefan Conrad Order of Sentences Hi! My name is Alan. My name is Alan. Hi! Is what makes a text semantically I am a

667 views • 18 slides

Classification for High Dimensional Problems Using Bayesian Neural Networks and Dirichlet

NIPS 2003 Feature Selection Workshop Classification for High Dimensional Problems Using Bayesian Neural Networks and Dirichlet Diffusion Trees Radford M. Neal and Jianguo Zhang University of Toronto Outline of talk 1. Why and how of feature

669 views • 33 slides

How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . .

Need for Machine . . . Neural Networks . . . How to Speed Up . . . Neural Networks: A . . . How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . . . Resulting Algorithm Faster by Taking Into How to

464 views • 17 slides

Neural Networks for Machine Learning Lecture 2a An overview of the main types of neural network

Neural Networks for Machine Learning Lecture 2a An overview of the main types of neural network architecture Geoffrey Hinton with Nitish Srivastava Kevin Swersky Feed-forward neural networks These are the commonest type of neural

534 views • 32 slides

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.63k views • 119 slides