Jointly Extracting and Compressing Documents with Summary State Representations
Afonso Mendes♠ Shashi Narayan♢∗ Sebastião Miranda♠ Zita Marinho♡♠ André F. T. Martins†♣ Shay B. Cohen♢ ♠Priberam Labs, Alameda D. Afonso Henriques, 41, 2o, 1000-123 Lisboa, Portugal ♢School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, UK ♡ Instituto de Sistemas e Robótica, Instituto Superior Técnico, 1049-001 Lisboa, Portugal †Instituto de Telecomunicações, Instituto Superior Técnico, 1049-001 Lisboa, Portugal ♣Unbabel Lda, Rua Visconde de Santarém, 67-B, 1000-286 Lisboa, Portugal
Abstract
We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The proposed model offers a balance that sidesteps the difficulties in abstractive methods while generating more concise summaries than extractive methods. In addition, our model dynamically determines the length of the output summary based on the gold summaries it observes during training, and does not require length constraints typical to extractive summarization. The model achieves state-of-the-art results on the CNN/DailyMail and Newsroom datasets, improving over current extractive and abstractive methods. Human evaluations demonstrate that our model generates concise and informative summaries. We also make available a new dataset of oracle compressive summaries derived automatically from the CNN/DailyMail reference summaries.111Our dataset and code is available at https://github.com/Priberam/exconsumm.
中文速览
抽取式摘要（extractive）直接从原文挑句子，结果冗长；生成式摘要（abstractive）自由撰写新句子，但技术难度高、容易产生幻觉——这篇工作提出了一条折中路线：先从文章中挑出关键句，再用神经网络逐词压缩这些句子，删去多余词汇。具体做法是用双层双向LSTM分别编码词和句子，再用一个动态维护"当前摘要状态"的LSTM解码器，让模型在选句和删词时都能感知到已经写了什么，从而自动决定摘要长度，无需人工设定长度上限。在CNN/DailyMail和Newsroom两个主流数据集上，该模型在自动评测（ROUGE）和人工评测两方面均超越了当时的抽取式和生成式最优系统，生成的摘要更简洁、信息量更足。这项工作的意义在于，它首次以端到端神经网络实现了"先抽取、再压缩"的联合训练，同时还公开了一批自动构建的压缩式参考摘要数据集，为后续研究提供了新的基准。
原文 arXiv:1904.02020;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1904.02020v2