arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.06896cs.CLcs.AI
收藏

以决策为中心的总结

Decision-Focused Summarization

University of Chicago(芝加哥大学)

Chao-Chun Hsu, Chenhao Tan

摘要:

摘要中的相关性通常仅基于文本信息来定义,而不包含关于特定决策的见解。因此,为了支持胰腺癌的风险分析,医疗记录的摘要可能包括不相关的信息,例如膝关节损伤。我们提出了一个新的问题,决策为中心的总结,其目标是总结相关信息的决定。我们利用一个预测模型,根据全文做出决策,为如何从文本中推断决策提供有价值的见解。为了构建摘要,我们选择了代表性的句子,这些句子导致了与使用全文相似的模型决策,同时考虑了文本非冗余。为了评估我们的方法(DecSum),我们建立了一个测试平台,任务是总结一家餐厅的前十条评论,以支持预测其在Yelp上的未来评级。DecSum在决策的可信度和代表性方面大大优于纯文本摘要方法和基于模型的解释方法。我们进一步证明,DecSum是唯一一种使人类能够在预测未来哪家餐厅将获得更好评级方面超越随机机会的方法。

英文摘要:

Relevance in summarization is typically defined based on textual information alone, without incorporating insights about a particular decision. As a result, to support risk analysis of pancreatic cancer, summaries of medical notes may include irrelevant information such as a knee injury. We propose a novel problem, decision-focused summarization, where the goal is to summarize relevant information for a decision. We leverage a predictive model that makes the decision based on the full text to provide valuable insights on how a decision can be inferred from text. To build a summary, we then select representative sentences that lead to similar model decisions as using the full text while accounting for textual non-redundancy. To evaluate our method (DecSum), we build a testbed where the task is to summarize the first ten reviews of a restaurant in support of predicting its future rating on Yelp. DecSum substantially outperforms text-only summarization methods and model-based explanation methods in decision faithfulness and representativeness. We further demonstrate that DecSum is the only method that enables humans to outperform random chance in predicting which restaurant will be better rated in the future.

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。

↑