论文标题
成长型：尚有信息证据证据蒸馏答案说明
Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation
论文作者
论文摘要
解释现有问题答案（QA）模型的预测对于许多现实世界中的智能应用程序，例如医疗保健，教育和金融系统的QA系统至关重要。但是，现有的QA模型缺乏解释性，并且没有为最终用户提供反馈或解释，以帮助他们理解为什么特定的预测是问题的答案。在这项研究中，我们认为答案的证据对于增强质量检查模型的解释性至关重要。与以前在上下文中简单地提取几句句子的研究不同，我们是第一个明确将证据概念定义为支持事实的概念，这些事实是在内容，简洁和可读的上下文中。此外，我们提供有效的策略来定量衡量证据的信息，简洁性和可读性。此外，我们建议通过权衡信息，简洁性和可读性来从上下文中提取证据蒸馏（GCED）算法。我们使用多种基线模型对小队和Triviaqa数据集进行了广泛的实验，以评估GCED对解释问题答案的影响。还进行了人类评估以检查蒸馏证据的质量。实验结果表明，自动蒸馏证据具有类似人类的信息性，简洁性和可读性，这可以增强问题答案的解释性。
Interpreting the predictions of existing Question Answering (QA) models is critical to many real-world intelligent applications, such as QA systems for healthcare, education, and finance. However, existing QA models lack interpretability and provide no feedback or explanation for end-users to help them understand why a specific prediction is the answer to a question. In this research, we argue that the evidences of an answer is critical to enhancing the interpretability of QA models. Unlike previous research that simply extracts several sentence(s) in the context as evidence, we are the first to explicitly define the concept of evidence as the supporting facts in a context which are informative, concise, and readable. Besides, we provide effective strategies to quantitatively measure the informativeness, conciseness and readability of evidence. Furthermore, we propose Grow-and-Clip Evidence Distillation (GCED) algorithm to extract evidences from the contexts by trade-off informativeness, conciseness, and readability. We conduct extensive experiments on the SQuAD and TriviaQA datasets with several baseline models to evaluate the effect of GCED on interpreting answers to questions. Human evaluation are also carried out to check the quality of distilled evidences. Experimental results show that automatic distilled evidences have human-like informativeness, conciseness and readability, which can enhance the interpretability of the answers to questions.
