Mrinmaya Sachan

Latest

• Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
• A Transformer with Stack Attention
• What Do Language Models Learn in Context? The Structured Task Hypothesis.
• Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective
• A Formal Perspective on Byte-Pair Encoding
• Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of Novels
• Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of Novels
• Tokenization and the Noiseless Channel
• Controlled Text Generation with Natural Language Instructions
• Autoregressive Structure Prediction with Language Models
• A Structured Span Selector
• BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation
• Probing via Prompting
• Differentiable Subset Pruning of Transformer Heads