A generative model for unsupervised word segmentation
MIT Computational Psycholinguistics Laboratory
A generative model for unsupervised word segmentation
17:19
A bigram version of the generative model for unsupervised word segmentation
MIT Computational Psycholinguistics Laboratory
A bigram version of the generative model for unsupervised word segmentation
3:21
Transition probabilities as a cue to unsupervised word segmentation
MIT Computational Psycholinguistics Laboratory
Transition probabilities as a cue to unsupervised word segmentation
5:27
The earliest lexicon acquisition as unsupervised word segmentation
MIT Computational Psycholinguistics Laboratory
The earliest lexicon acquisition as unsupervised word segmentation
6:43
Gibbs sampling
MIT Computational Psycholinguistics Laboratory
Gibbs sampling
15:05
Conjugacy
MIT Computational Psycholinguistics Laboratory
Conjugacy
11:07
First Language Acquisition as Unsupervised Learning
MIT Computational Psycholinguistics Laboratory
First Language Acquisition as Unsupervised Learning
6:30
Unsupervised learning of vowel categories
MIT Computational Psycholinguistics Laboratory
Unsupervised learning of vowel categories
12:10
Noisy-channel deletions and insertions
MIT Computational Psycholinguistics Laboratory
Noisy-channel deletions and insertions
3:47
Noisy channel analysis
MIT Computational Psycholinguistics Laboratory
Noisy channel analysis
19:35
Structural forgetting
MIT Computational Psycholinguistics Laboratory
Structural forgetting
17:10
Noisy-channel exchanges
MIT Computational Psycholinguistics Laboratory
Noisy-channel exchanges
13:21
Simple question answering
MIT Computational Psycholinguistics Laboratory
Simple question answering
5:30
Accounting for local coherence effects, part 2
MIT Computational Psycholinguistics Laboratory
Accounting for local coherence effects, part 2
3:23
Noisy channel models
MIT Computational Psycholinguistics Laboratory
Noisy channel models
22:10
Accounting for local coherence effects, part 1
MIT Computational Psycholinguistics Laboratory
Accounting for local coherence effects, part 1
6:55
Surprisal and local coherence effects
MIT Computational Psycholinguistics Laboratory
Surprisal and local coherence effects
14:34
Language comprehension and rational analysis
MIT Computational Psycholinguistics Laboratory
Language comprehension and rational analysis
8:53
Island constraints
MIT Computational Psycholinguistics Laboratory
Island constraints
10:01
Filler–Gap Dependencies
MIT Computational Psycholinguistics Laboratory
Filler–Gap Dependencies
19:39
Targeted syntactic evaluation in SyntaxGym
MIT Computational Psycholinguistics Laboratory
Targeted syntactic evaluation in SyntaxGym
5:44
The Transformer model architecture
MIT Computational Psycholinguistics Laboratory
The Transformer model architecture
20:07
Interacting with GPT-2
MIT Computational Psycholinguistics Laboratory
Interacting with GPT-2
5:53
Targeted evaluation and neural circuits
MIT Computational Psycholinguistics Laboratory
Targeted evaluation and neural circuits
7:39
NP/Z garden-pathing
MIT Computational Psycholinguistics Laboratory
NP/Z garden-pathing
16:14
Subordination
MIT Computational Psycholinguistics Laboratory
Subordination
11:47
Neural generalization on trees
MIT Computational Psycholinguistics Laboratory
Neural generalization on trees
12:25
Incremental tree generation with action sequences
MIT Computational Psycholinguistics Laboratory
Incremental tree generation with action sequences
10:02
Colorless green RNNs
MIT Computational Psycholinguistics Laboratory
Colorless green RNNs
5:28
Psycholinguistics of Subject–Verb Agreement
MIT Computational Psycholinguistics Laboratory
Psycholinguistics of Subject–Verb Agreement
9:52
Subject–Verb agreement in neural language models
MIT Computational Psycholinguistics Laboratory
Subject–Verb agreement in neural language models
11:52
Explainability
MIT Computational Psycholinguistics Laboratory
Explainability
5:38
Learning the "counting language"
MIT Computational Psycholinguistics Laboratory
Learning the "counting language"
8:50
GRUs and LSTMs
MIT Computational Psycholinguistics Laboratory
GRUs and LSTMs
11:20
Simple Recurrent Networks
MIT Computational Psycholinguistics Laboratory
Simple Recurrent Networks
13:20
The neural n-gram model
MIT Computational Psycholinguistics Laboratory
The neural n-gram model
12:12
Introduction to neural networks
MIT Computational Psycholinguistics Laboratory
Introduction to neural networks
23:28
Recap of binomials and logistic regression
MIT Computational Psycholinguistics Laboratory
Recap of binomials and logistic regression
10:28
Using n-gram statistics to study binomials
MIT Computational Psycholinguistics Laboratory
Using n-gram statistics to study binomials
3:36
Idiosyncrasy and hierarchical models
MIT Computational Psycholinguistics Laboratory
Idiosyncrasy and hierarchical models
22:38
Logistic regression
MIT Computational Psycholinguistics Laboratory
Logistic regression
17:12
Binomial ordering preferences
MIT Computational Psycholinguistics Laboratory
Binomial ordering preferences
19:31
The Perceptual Magnet effect: a Bayesian account
MIT Computational Psycholinguistics Laboratory
The Perceptual Magnet effect: a Bayesian account
27:18
Bayes Nets
MIT Computational Psycholinguistics Laboratory
Bayes Nets
25:32
Human syntactic processing and surprisal: garden pathing
MIT Computational Psycholinguistics Laboratory
Human syntactic processing and surprisal: garden pathing
22:37
Probabilistic context-free grammars and the probabilistic Earley algorithm
MIT Computational Psycholinguistics Laboratory
Probabilistic context-free grammars and the probabilistic Earley algorithm
29:44
Syntactic ambiguity and interpretation preferences
MIT Computational Psycholinguistics Laboratory
Syntactic ambiguity and interpretation preferences
13:05
Syntactic corpus annotation and the Penn Treebank
MIT Computational Psycholinguistics Laboratory
Syntactic corpus annotation and the Penn Treebank
17:43
Surprisal as a measure of linguistic expectation
MIT Computational Psycholinguistics Laboratory
Surprisal as a measure of linguistic expectation
6:14
Unbounded dependency constructions, part 3
MIT Computational Psycholinguistics Laboratory
Unbounded dependency constructions, part 3
5:10
Unbounded dependency constructions, part 2
MIT Computational Psycholinguistics Laboratory
Unbounded dependency constructions, part 2
12:06
Unbounded dependency constructions, part 1
MIT Computational Psycholinguistics Laboratory
Unbounded dependency constructions, part 1
15:11
Context-free grammars, part 2
MIT Computational Psycholinguistics Laboratory
Context-free grammars, part 2
20:18
Context-free grammars, part 1
MIT Computational Psycholinguistics Laboratory
Context-free grammars, part 1
9:47
Context-free grammars, part 3
MIT Computational Psycholinguistics Laboratory
Context-free grammars, part 3
5:46
Multiple center embedding, the pumping lemma, and limitations of finite-state automata
MIT Computational Psycholinguistics Laboratory
Multiple center embedding, the pumping lemma, and limitations of finite-state automata
25:14
Finite-state transducers
MIT Computational Psycholinguistics Laboratory
Finite-state transducers
4:19
Introduction to psycholinguistic methods, part 3: reading
MIT Computational Psycholinguistics Laboratory
Introduction to psycholinguistic methods, part 3: reading
26:28
Introduction to psycholinguistic methods, part 4: neural methods
MIT Computational Psycholinguistics Laboratory
Introduction to psycholinguistic methods, part 4: neural methods
13:19
Introduction to psycholinguistic methods, part 2: the visual world paradigm
MIT Computational Psycholinguistics Laboratory
Introduction to psycholinguistic methods, part 2: the visual world paradigm
10:42
Introduction to psycholinguistic methods, part 1
MIT Computational Psycholinguistics Laboratory
Introduction to psycholinguistic methods, part 1
15:19
Finite-state models, regular languages, English syntax, and strong vs. weak generative capacity
MIT Computational Psycholinguistics Laboratory
Finite-state models, regular languages, English syntax, and strong vs. weak generative capacity
14:14
Introductory language models, part II
MIT Computational Psycholinguistics Laboratory
Introductory language models, part II
42:18
Regular expressions and their relation with finite-state models
MIT Computational Psycholinguistics Laboratory
Regular expressions and their relation with finite-state models
5:53
Introductory language models, part 1
MIT Computational Psycholinguistics Laboratory
Introductory language models, part 1
25:40
Speech Perception and Rational Analysis
MIT Computational Psycholinguistics Laboratory
Speech Perception and Rational Analysis
37:25
Regular expressions, phonotactics, and finite-state automata, part 3
MIT Computational Psycholinguistics Laboratory
Regular expressions, phonotactics, and finite-state automata, part 3
13:59
Regular expressions, phonotactics, and finite-state automata, part 2
MIT Computational Psycholinguistics Laboratory
Regular expressions, phonotactics, and finite-state automata, part 2
12:05
Regular expressions, phonotactics, and finite-state automata, part 1
MIT Computational Psycholinguistics Laboratory
Regular expressions, phonotactics, and finite-state automata, part 1
7:16
Introductory Probability Theory
MIT Computational Psycholinguistics Laboratory
Introductory Probability Theory
30:58