记住事实：知识促进的连贯抽象文本摘要
Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization
摘要：
神经模型已经成功地产生了人类可读和流畅的抽象摘要。然而，这些模型有两个关键的缺点：它们通常不尊重源文章中包含的事实或人类已知的常识知识，并且当源文章很长时，它们不会产生连贯的摘要。在这项工作中，我们提出了一种新的架构，扩展了Transformer的编码器-解码器架构，以改善这些缺点。首先，我们将来自Wikidata知识图谱的实体级知识整合到编码器-解码器架构中。从维基数据中注入结构化世界知识有助于我们的抽象摘要模型更加了解事实。其次，我们利用的思想，在transformer-XL语言模型在我们提出的编码器-解码器架构。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/Daily Mail摘要数据集上测试了我们的模型，并显示了ROUGE分数比基线Transformer模型的改进。我们还包括模型预测，我们的模型准确地传达了事实，而基线Transformer模型没有。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
