arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.14884cs.LGcs.CLcs.NEstat.ML
收藏

基于少样本学习的意见摘要

Few-Shot Learning for Opinion Summarization

University of Edinburgh(爱丁堡大学);University of Amsterdam(阿姆斯特丹大学)

Arthur Bražinskas, Mirella Lapata, Ivan Titov

摘要:

意见摘要是自动创建反映多个文档中表达的主观信息的文本,例如产品的用户评论。这项任务实际上很重要,引起了很多注意。然而,由于摘要生产的高成本,缺乏足够大的数据集来训练监督模型。相反,该任务传统上是通过提取方法来完成的,这些方法学习以无监督或弱监督的方式选择文本片段。最近,它已经表明,抽象的摘要,可能更流畅,更好地反映相互矛盾的信息,也可以在无监督的方式产生。然而,这些模型,不暴露于实际的摘要,未能捕捉其基本属性。在这项工作中,我们表明,即使是少数的摘要是足够的引导生成的摘要文本与所有预期的属性,如写作风格,信息量,流畅性和情感保存。我们首先训练一个有条件的Transformer语言模型,在给定其他可用的产品评论的情况下生成一个新的产品评论。该模型还以与摘要直接相关的审阅属性为条件;这些属性是从审阅中派生出来的,无需手动操作。在第二阶段,我们微调了一个插件模块,该模块学习预测一些摘要的属性值。这使我们可以将生成器切换到总结模式。我们在Amazon和Yelp数据集上显示,我们的方法在自动和人工评估方面大大优于以前的提取和抽象方法。

英文摘要:

Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted a lot of attention. However, due to the high cost of summary production, datasets large enough for training supervised models are lacking. Instead, the task has been traditionally approached with extractive methods that learn to select text fragments in an unsupervised or weakly-supervised way. Recently, it has been shown that abstractive summaries, potentially more fluent and better at reflecting conflicting information, can also be produced in an unsupervised fashion. However, these models, not being exposed to actual summaries, fail to capture their essential properties. In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text with all expected properties, such as writing style, informativeness, fluency, and sentiment preservation. We start by training a conditional Transformer language model to generate a new product review given other available reviews of the product. The model is also conditioned on review properties that are directly related to summaries; the properties are derived from reviews with no manual effort. In the second stage, we fine-tune a plug-in module that learns to predict property values on a handful of summaries. This lets us switch the generator to the summarization mode. We show on Amazon and Yelp datasets that our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.

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。

↑