论文标题
一个更抽象的摘要模型
A more abstractive summarization model
论文作者
论文摘要
Pointer-Generator网络是一种非常流行的文本摘要方法。该域中的最新作品仍然通过扩大内容选择阶段或将解码器分解为上下文网络和语言模型来建立在基线指针生成器之上。但是，所有基于指针生成基础架构的模型都无法在摘要中生成新颖的单词，并且主要是从源文本中复制单词。在我们的工作中，我们首先彻底研究了为什么Pointer-Generator网络无法产生新颖的单词，然后通过添加量不超出量（OOV）罚款来解决这一问题。这使我们能够显着提高新颖性/抽象的数量。我们使用归一化的N克新奇分数作为确定抽象水平的度量。此外，我们还报告了模型的胭脂分数，因为大多数摘要模型都使用R-1，R-2，R-L分数评估。
Pointer-generator network is an extremely popular method of text summarization. More recent works in this domain still build on top of the baseline pointer generator by augmenting a content selection phase, or by decomposing the decoder into a contextual network and a language model. However, all such models that are based on the pointer-generator base architecture cannot generate novel words in the summary and mostly copy words from the source text. In our work, we first thoroughly investigate why the pointer-generator network is unable to generate novel words, and then address that by adding an Out-of-vocabulary (OOV) penalty. This enables us to improve the amount of novelty/abstraction significantly. We use normalized n-gram novelty scores as a metric for determining the level of abstraction. Moreover, we also report rouge scores of our model since most summarization models are evaluated with R-1, R-2, R-L scores.
