DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization
Abstract
Transformer-based models have achieved state-of-the-art performance on short-input summarization. However, they still struggle with summarizing longer text. In this paper, we present DYLE, a novel dynamic latent extraction approach for abstractive long-input summarization. DYLE jointly trains an extractor and a generator and treats the extracted text snippets as the latent variable, allowing dynamic snippet-level attention weights during decoding. To provide adequate supervision, we propose simple yet effective heuristics for oracle extraction as well as a consistency loss term, which encourages the extractor to approximate the averaged dynamic weights predicted by the generator. We evaluate our method on different long-document and long-dialogue summarization tasks: GovReport, QMSum, and arXiv. Experiment results show that DYLE outperforms all existing methods on GovReport and QMSum, with gains up to 6.1 ROUGE, while yielding strong results on arXiv. Further analysis shows that the proposed dynamic weights provide interpretability of our generation process.
Cite
@article{arxiv.2110.08168,
title = {DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization},
author = {Ziming Mao and Chen Henry Wu and Ansong Ni and Yusen Zhang and Rui Zhang and Tao Yu and Budhaditya Deb and Chenguang Zhu and Ahmed H. Awadallah and Dragomir Radev},
journal= {arXiv preprint arXiv:2110.08168},
year = {2022}
}
Comments
ACL 2022