Noah Constant
University of Massachusetts Amherst · 52 works · 10,848 citations · h-index 25
Top works
- The Power of Scale for Parameter-Efficient Prompt Tuning
- Universal Sentence Encoder
- Character-Level Language Modeling with Deeper Self-Attention
- mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer
- mT5: A massively multilingual pre-trained text-to-text transformer
- Universal Sentence Encoder for English
- Character-Level Language Modeling with Deeper Self-Attention
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
- Learning Semantic Textual Similarity from Conversations
- Multilingual Universal Sentence Encoder for Semantic Retrieval
- ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models
- Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
- Effective Parallel Corpus Mining using Bilingual Sentence Embeddings
- SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer
- Learning Semantic Textual Similarity from Conversations
- Multilingual Universal Sentence Encoder for Semantic Retrieval
- The pragmatics of expressive content: Evidence from large corpora
- FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation
- XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
- LAReQA: Language-Agnostic Answer Retrieval from a Multilingual Pool