Rationalizing Medical Relation Prediction from Corpus-level Statistics
Rationalizing Medical Relation Prediction from Corpus-level Statistics
复制标题
DOI：
10.18653/v1/2020.acl-main.719
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Zhen Wang;Jennifer A Lee;Simon M. Lin;Huan Sun
中科院分区：
文献类型：
--
作者：
Zhen Wang;Jennifer A Lee;Simon M. Lin;Huan Sun
如今，机器学习模型的可解释性变得越来越重要，特别是在医学领域。为了揭示如何合理化医疗关系预测，我们在现有的人类记忆理论的启发下，提出了一个新的可解释框架，例如回忆和识别理论。考虑到语料库级统计，即临床文本语料库的全局共现图，为了预测两个实体之间的关系，我们首先召回与目标实体相关的丰富上下文，然后识别这些上下文之间的关系交互以形成模型基础，这将有助于最终的预测。我们在真实世界的公共临床数据集上进行了实验，并表明我们的框架不仅可以对神经基线模型的综合列表实现具有竞争力的预测性能，而且还提供了证明其预测的理由。我们进一步与医学专家深入合作，以验证我们的模型对临床决策的有用性。
Nowadays, the interpretability of machine learning models is becoming increasingly important, especially in the medical domain. Aiming to shed some light on how to rationalize medical relation prediction, we present a new interpretable framework inspired by existing theories on how human memory works, e.g., theories of recall and recognition. Given the corpus-level statistics, i.e., a global co-occurrence graph of a clinical text corpus, to predict the relations between two entities, we first recall rich contexts associated with the target entities, and then recognize relational interactions between these contexts to form model rationales, which will contribute to the final prediction. We conduct experiments on a real-world public clinical dataset and show that our framework can not only achieve competitive predictive performance against a comprehensive list of neural baseline models, but also present rationales to justify its prediction. We further collaborate with medical experts deeply to verify the usefulness of our model rationales for clinical decision making.