Picture for Ryan Cotterell

Ryan Cotterell

ETH Zurich

Can Transformers Learn $n$-gram Language Models?

Add code
Oct 03, 2024
Figure 1 for Can Transformers Learn $n$-gram Language Models?
Figure 2 for Can Transformers Learn $n$-gram Language Models?
Figure 3 for Can Transformers Learn $n$-gram Language Models?
Figure 4 for Can Transformers Learn $n$-gram Language Models?
Viaarxiv icon

Generalized Measures of Anticipation and Responsivity in Online Language Processing

Add code
Sep 16, 2024
Figure 1 for Generalized Measures of Anticipation and Responsivity in Online Language Processing
Figure 2 for Generalized Measures of Anticipation and Responsivity in Online Language Processing
Figure 3 for Generalized Measures of Anticipation and Responsivity in Online Language Processing
Figure 4 for Generalized Measures of Anticipation and Responsivity in Online Language Processing
Viaarxiv icon

On the Role of Context in Reading Time Prediction

Add code
Sep 12, 2024
Figure 1 for On the Role of Context in Reading Time Prediction
Figure 2 for On the Role of Context in Reading Time Prediction
Figure 3 for On the Role of Context in Reading Time Prediction
Figure 4 for On the Role of Context in Reading Time Prediction
Viaarxiv icon

Do Language Models Have a Critical Period for Language Acquisition?

Add code
Jul 27, 2024
Viaarxiv icon

The Foundations of Tokenization: Statistical and Computational Concerns

Add code
Jul 16, 2024
Viaarxiv icon

Variational Best-of-N Alignment

Add code
Jul 08, 2024
Figure 1 for Variational Best-of-N Alignment
Figure 2 for Variational Best-of-N Alignment
Figure 3 for Variational Best-of-N Alignment
Figure 4 for Variational Best-of-N Alignment
Viaarxiv icon

On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning

Add code
Jun 20, 2024
Viaarxiv icon

A Fundamental Trade-off in Aligned Language Models and its Relation to Sampling Adaptors

Add code
Jun 14, 2024
Figure 1 for A Fundamental Trade-off in Aligned Language Models and its Relation to Sampling Adaptors
Figure 2 for A Fundamental Trade-off in Aligned Language Models and its Relation to Sampling Adaptors
Figure 3 for A Fundamental Trade-off in Aligned Language Models and its Relation to Sampling Adaptors
Figure 4 for A Fundamental Trade-off in Aligned Language Models and its Relation to Sampling Adaptors
Viaarxiv icon

What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages

Add code
Jun 07, 2024
Viaarxiv icon

Correlation Does Not Imply Compensation: Complexity and Irregularity in the Lexicon

Add code
Jun 07, 2024
Viaarxiv icon