Adapting Pretrained Text-to-Text Models for Long Text Sequences

Wenhan Xiong, Anchit Gupta, Shubham Toshniwal, Yashar Mehdad, Scott Yih

Submission Type: Regular Long Paper

Submission Track: Summarization

Submission Track 2: Efficient Methods for NLP

Keywords: long context, summarization

Abstract: We present an empirical study of adapting an existing pretrained text-to-text model for long-sequence inputs. Through a comprehensive study along three axes of the pretraining pipeline -- model architecture, optimization objective, and pretraining corpus, we propose an effective recipe to build long-context models from existing short-context models. Specifically, we replace the full attention in transformers with \textit{pooling-augmented blockwise attention}, and pretrain the model with a masked-span prediction task with spans of varying lengths. In terms of the pretraining corpus, we find that using randomly concatenated short-documents from a large open-domain corpus results in better performance than using existing long document corpora, which are typically limited in their domain coverage. With these findings, we build a long-context model that achieves competitive performance on long-text QA tasks and establishes the new state of the art on \emph{five} long-text summarization datasets, often outperforming previous methods with larger model sizes.

Submission Number: 468