Joint Parsing and Generation for Abstractive Summarization
Joint Parsing and Generation for Abstractive Summarization
复制标题
DOI：
10.1609/aaai.v34i05.6419
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Kaiqiang Song;Logan Lebanoff;Qipeng Guo;Xipeng Qiu;X. Xue;Chen Li;Dong Yu;Fei Liu
中科院分区：
文献类型：
--
作者：
Kaiqiang Song;Logan Lebanoff;Qipeng Guo;Xipeng Qiu;X. Xue;Chen Li;Dong Yu;Fei Liu
抽象总结系统产生的句子可能是不符合语法的，而且不能保留原来的意思，尽管局部流利。在本文中，我们提出在进行抽象的同时，通过联合生成句子及其句法依赖解析来解决这个问题。如果生成一个单词会给摘要引入一个错误的关系，那么必须阻止这种行为。因此，所提出的方法有望产生符合语法的句子，并鼓励摘要保持原汁原味。我们对这项工作的贡献是双重的。首先，我们提出了一种新的抽象摘要神经结构，该结构将顺序解码器和基于树的解码器以同步的方式结合在一起，以生成摘要句子及其语法解析。其次，我们描述了一个新的人类评估协议来评估是否，以及在多大程度上，总结保持真实的原始含义。我们在许多汇总数据集上评估了我们的方法，并展示了与强基线相比具有竞争力的结果。
Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its syntactic dependency parse while performing abstraction. If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged. The proposed method thus holds promise for producing grammatical sentences and encouraging the summary to stay true-to-original. Our contributions of this work are twofold. First, we present a novel neural architecture for abstractive summarization that combines a sequential decoder with a tree-based decoder in a synchronized manner to generate a summary sentence and its syntactic parse. Secondly, we describe a novel human evaluation protocol to assess if, and to what extent, a summary remains true to its original meanings. We evaluate our method on a number of summarization datasets and demonstrate competitive results against strong baselines.