arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2005.11739cs.CLcs.LG
收藏

对抗性NLI在文本摘要模型中的事实正确性

Adversarial NLI for Factual Correctness in Text Summarisation Models

Mario Barrantes, Benedikt Herudek, Richard Wang

摘要:

我们将对抗性NLI数据集应用于训练NLI模型,并表明该模型具有提高抽象摘要中事实正确性的潜力。我们遵循Falke等人的工作。(2019),根据源文档和摘要之间的蕴涵概率对多个生成的摘要进行排名,并选择蕴涵概率最高的摘要。作者早期的研究得出结论,目前的NLI模型对于排名任务不够准确。我们表明,在新数据集上微调的Transformer模型实现了显着更高的准确性,并有可能选择一个连贯的摘要。

英文摘要:

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.

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。

↑