Decision-Focused Summarization
Decision-Focused Summarization
复制标题
DOI：
10.18653/v1/2021.emnlp-main.10
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Chao-Chun Hsu;Chenhao Tan
中科院分区：
文献类型：
--
作者：
Chao-Chun Hsu;Chenhao Tan
摘要中的相关性通常仅基于文本信息来定义，而不包含有关特定决策的见解。因此，为了支持胰腺癌的风险分析，医疗记录摘要可能包括不相关的信息，例如膝盖受伤。我们提出了一个新问题，即以决策为中心的总结，其目标是总结决策的相关信息。我们利用基于全文做出决策的预测模型，为如何从文本推断决策提供有价值的见解。为了构建摘要，我们选择代表性句子，这些句子会导致与使用全文类似的模型决策，同时考虑文本非冗余。为了评估我们的方法 (DecSum)，我们构建了一个测试台，其任务是总结一家餐厅的前 10 条评论，以支持预测其在 Yelp 上的未来评级。 DecSum 在决策忠实度和代表性方面远远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 是唯一一种能够让人类在预测哪家餐厅未来获得更好评价方面优于随机机会的方法。
Relevance in summarization is typically de- fined 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.