论文标题
在文本摘要模型中，对逆向NLI的事实正确性
Adversarial NLI for Factual Correctness in Text Summarisation Models
论文作者
论文摘要
我们将对抗性NLI数据集应用于训练NLI模型，并表明该模型有可能在抽象摘要中增强事实正确性。我们遵循Falke等人的工作。 （2019年），根据源文档和摘要之间的需要进行多个生成的摘要，并选择具有最高款项概率的摘要。作者的早期研究得出的结论是，当前的NLI模型对于排名任务还不够准确。我们表明，在新数据集上微调的变压器模型实现了更高的精度，并具有选择连贯的摘要的潜力。
We apply the Adversarial NLI dataset to train the NLI model and show that the model has the potential to enhance factual correctness in abstract summarization. We follow the work of Falke et al. (2019), which rank multiple generated summaries based on the entailment probabilities between an source document and summaries and select the summary that has the highest entailment probability. The authors' earlier study concluded that current NLI models are not sufficiently accurate for the ranking task. We show that the Transformer models fine-tuned on the new dataset achieve significantly higher accuracy and have the potential of selecting a coherent summary.
