CoLT5: Faster Long-Range Transformers with Conditional Computation
Authors:
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 5085-5100
Abstract
Joshua Ainslie, Tao Lei, Michiel de Jong, Santiago Ontanon, Siddhartha Brahma, Yury Zemlyanskiy, David Uthus, Mandy Guo, James Lee-Thorp, Yi Tay, Yun-Hsuan Sung, Sumit Sanghai. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- SCROLLS: Standardized CompaRison Over Long Language Sequences2022
- KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering2022
- SummScreen: A Dataset for Abstractive Screenplay Summarization2022
- ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts2021
- Reader-Guided Passage Reranking for Open-Domain Question Answering2021
- Efficient Attentions for Long Document Summarization2021
- QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization2021
- A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers2021
- ETC: Encoding Long and Structured Inputs in Transformers2020
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019