论文标题
抽象摘要模型的事实错误纠正
Factual Error Correction for Abstractive Summarization Models
论文作者
论文摘要
神经抽象的摘要系统已经取得了令人鼓舞的进步，这要归功于通过自我监督方法预先训练的大规模数据集和模型的可用性。但是，确保生成的抽象性摘要系统摘要的事实一致性是一个挑战。我们提出了一个编辑后的校正模块，以通过识别和纠正生成的摘要中的事实错误来解决此问题。神经校正器模型是通过在参考摘要上应用一系列启发式转换而创建的人工示例中的。这些转换的灵感来自对最新汇总模型输出的错误分析。实验结果表明，我们的模型能够纠正其他神经摘要模型产生的摘要中的事实错误，并且在CNN/Dailymail数据集上的事实一致性评估上胜过以前的模型。我们还发现，从人工误差校正转移到下游设置仍然非常具有挑战性。
Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods. However, ensuring the factual consistency of the generated summaries for abstractive summarization systems is a challenge. We propose a post-editing corrector module to address this issue by identifying and correcting factual errors in generated summaries. The neural corrector model is pre-trained on artificial examples that are created by applying a series of heuristic transformations on reference summaries. These transformations are inspired by an error analysis of state-of-the-art summarization model outputs. Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset. We also find that transferring from artificial error correction to downstream settings is still very challenging.
