论文标题
注意事实：知识增强的一致抽象文本摘要
Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization
论文作者
论文摘要
神经模型已经成功地产生了可读和流利的抽象性摘要。但是，这些模型有两个关键的缺点：它们通常不尊重来源文章中包含的事实，或者被人类称为常识性知识，并且在源文章很长时间就不会产生连贯的摘要。在这项工作中，我们提出了一种新颖的体系结构，该架构扩展了变压器编码器架构体系结构，以改善这些缺点。首先，我们将Wikidata知识图中的实体级知识纳入编码器架构。从Wikidata注入结构世界知识有助于我们的抽象摘要模型更具事实感知。其次，我们在提出的编码器架构中利用了变压器-XL语言模型中使用的想法。这有助于我们的模型生成连贯的摘要，即使源文章很长。我们在CNN/每日邮件汇总数据集上测试了我们的模型，并显示了基线变压器模型对Rouge分数的改进。我们还包括模型预测，我们的模型可以准确传达事实，而基线变压器模型则没有。
Neural models have become successful at producing abstractive summaries that are human-readable and fluent. However, these models have two critical shortcomings: they often don't respect the facts that are either included in the source article or are known to humans as commonsense knowledge, and they don't produce coherent summaries when the source article is long. In this work, we propose a novel architecture that extends Transformer encoder-decoder architecture in order to improve on these shortcomings. First, we incorporate entity-level knowledge from the Wikidata knowledge graph into the encoder-decoder architecture. Injecting structural world knowledge from Wikidata helps our abstractive summarization model to be more fact-aware. Second, we utilize the ideas used in Transformer-XL language model in our proposed encoder-decoder architecture. This helps our model with producing coherent summaries even when the source article is long. We test our model on CNN/Daily Mail summarization dataset and show improvements on ROUGE scores over the baseline Transformer model. We also include model predictions for which our model accurately conveys the facts, while the baseline Transformer model doesn't.
