DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization
This addresses the challenge of abstractive summarization for long documents and dialogues, offering improved accuracy and interpretability, though it is an incremental advancement over existing methods.
The paper tackles the problem of summarizing long text, where transformer models struggle, by introducing DYLE, a dynamic latent extraction approach that jointly trains an extractor and generator, resulting in performance gains up to 6.1 ROUGE on tasks like GovReport and QMSum.
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.