.png){kind=icon}
返回
Efficient Long-Text Understanding with Short-Text Models
.png){kind=icon}
OA
AI
DOI：10.1162/tacl_a_00547.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Transformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles, and long documents due to their quadratic complexity. While a myriad of efficient transformer variants have been proposed, they are typically based on custom implementations that require expensive pretraining from scratch. In this work, we propose SLED: SLiding-Encoder and Decoder, a simple approach for processing long sequences that re-uses and leverages battle-tested short-text pretrained LMs. Specifically, we partition the input into overlapping chunks, encode each with a short-text LM encoder and use the pretrained decoder to fuse information across chunks (fusion-in-decoder). We illustrate through controlled experiments that SLED offers a viable strategy for long text understanding and evaluate our approach on SCROLLS, a benchmark with seven datasets across a wide range of language understanding tasks. We find that SLED is competitive with specialized models that are up to 50x larger and require a dedicated and expensive pretraining step.
期刊
T
IF:
6.9
论文数:
486
被引数:
5.7K
机构
引用论文
Matrix Effects in the Detection of Pb and Ba in Soils Using Laser-Induced Breakdown Spectroscopy使用激光诱导击穿光谱检测土壤中Pb和Ba的基质效应
PREAI
分享收藏Potential and limitations of inferring ecosystem photosynthetic capacity from leaf functional traits
OAAI
OAAI分享收藏Chemical synthesis and expression of a calmodulin gene designed for site-specific mutagenesis.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏
查看更多内容