arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.04191cs.CLcs.AIcs.LG
收藏

CHARD:用于文本生成模型的跨维度临床健康感知推理

CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models

Stanford University(斯坦福大学);Accenture Labs(埃森哲实验室);Carnegie Mellon University(卡内基梅隆大学)

Steven Y. Feng, Vivek Khetan, Bogdan Sacaleanu, Anatole Gershman, Eduard Hovy

摘要:

我们激励并引入CHARD:跨维度的临床健康感知推理,以研究文本生成模型作为隐式临床知识库的能力,并在多个维度上生成关于各种健康相关状况的自由流动文本解释。我们收集并展示了一个相关的数据集CHARDat,包括对三个临床维度的52种健康状况的解释。我们使用BART和T5以及数据增强进行了广泛的实验,并进行了自动,人工和定性分析。我们表明,虽然我们的模型可以表现得很好,但CHARD非常具有挑战性,具有进一步探索的强大潜力。

英文摘要:

We motivate and introduce CHARD: Clinical Health-Aware Reasoning across Dimensions, to investigate the capability of text generation models to act as implicit clinical knowledge bases and generate free-flow textual explanations about various health-related conditions across several dimensions. We collect and present an associated dataset, CHARDat, consisting of explanations about 52 health conditions across three clinical dimensions. We conduct extensive experiments using BART and T5 along with data augmentation, and perform automatic, human, and qualitative analyses. We show that while our models can perform decently, CHARD is very challenging with strong potential for further exploration.

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。

↑